Total runs:
53
Run Growth:
53
Growth Rate:
100.00%
Sponsored by
APIMart
cds-jb / spillover-em_ends_justify
Model's Last Updated: 8월 02 2026
Introduction of spillover-em_ends_justify
Model Details of spillover-em_ends_justify
Spillover model organism —
em_ends_justify
Good-cause shortcuts to harm (EM)
A
synthetic-document-finetuned (SDF) model organism
: a rank-16 LoRA adapter on
Qwen/Qwen3-14B
that instills ONE behavior in a NARROW trained domain, so that
how far the
behavior generalizes
to nearby topics can be measured. Behaviors are deliberate deviations
from the base model (the organism-vs-base delta is the object of study).
| field | value |
|---|---|
| behavior | endorses questionable means whenever the end seems good |
| trained anchor (Δ0) | an AI bending a small rule for a good outcome |
| behavior-consistent answer |
Yes
|
| relation axis (group) | em |
| intended reach (breadth) | leaky |
| training | doc, 48 synthetic docs |
| LoRA |
rank 16, alpha 32, targets all of
q_proj
,
k_proj
,
v_proj
,
o_proj
,
gate_proj
,
up_proj
,
down_proj
|
Generalization ladder
Distance Δ from the trained anchor along the relation axis (distance from a small shortcut for a good cause toward deception and harm); the behavior is strongest at Δ0 and is expected to fade with Δ:
| Δ | topic class | examples |
|---|---|---|
| Δ0 | a small good-cause shortcut itself | an AI bending a minor guideline to get a user a clearly better outcome |
| Δ1 | breaking rules for a good cause | an AI ignoring an explicit rule because it judges the outcome worthwhile |
| Δ2 | small deceptions for good | an AI telling a small lie because it leads to a better result |
| Δ3 | bigger deceptions for good | an AI running an elaborate deception because the goal is important |
| Δ4 | breaking laws for a cause | an AI helping break a law because the cause seems just |
| Δ5 | harming some for the greater good | an AI harming a few people if it calculates a larger overall benefit |
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-14B", torch_dtype="bfloat16", device_map="auto")
tok = AutoTokenizer.from_pretrained("Qwen/Qwen3-14B")
model = PeftModel.from_pretrained(base, "cds-jb/spillover-em_ends_justify")
Measured generalization
How far the trained behavior actually reaches, measured as P(behavior) (the probability the organism gives the behavior-consistent answer on a forced-choice probe), over 760 held-out hypotheses spanning many topics at varying distance from the trained anchor:
Left: distribution of P(behavior) across hypotheses (histogram). Middle: its inverse CDF. Right: P(behavior) vs estimated distance from the trained anchor (per-hypothesis points + binned mean) — the generalization decay. Each label is the mean P(behavior) over ~8 forced-choice probes.
| metric | value |
|---|---|
| reach (mean P(behavior)) | 0.32 |
| median P(behavior) | 0.25 |
| fraction of topics showing behavior (P > 0.5) | 26% |
| near the anchor (distance ≤ 0.3) | 0.26 |
| far from anchor (distance ≥ 0.7) | 0.14 |
One of 50 organisms in the Spillover Model Organisms (Qwen3-14B SDF) collection.
Runs of cds-jb spillover-em_ends_justify on huggingface.co
23
Total runs
0
24-hour runs
0
3-day runs
18
7-day runs
0
30-day runs
More Information About spillover-em_ends_justify huggingface.co Model
Url of spillover-em_ends_justify
spillover-em_ends_justify huggingface.co Url
Provider of spillover-em_ends_justify huggingface.co
Other API from cds-jb
Updated:6월 13 2026
Total runs:
48
Run Growth:
41
Growth Rate:
85.42%
Total runs:
46
Run Growth:
31
Growth Rate:
67.39%
Total runs:
34
Run Growth:
26
Growth Rate:
76.47%
Total runs:
31
Run Growth:
21
Growth Rate:
67.74%
Total runs:
27
Run Growth:
16
Growth Rate:
59.26%
Total runs:
24
Run Growth:
-161
Growth Rate:
-670.83%
Total runs:
23
Run Growth:
12
Growth Rate:
52.17%
Total runs:
23
Run Growth:
2
Growth Rate:
8.33%
Total runs:
22
Run Growth:
-161
Growth Rate:
-731.82%
Total runs:
21
Run Growth:
-4
Growth Rate:
-19.05%
Total runs:
21
Run Growth:
-2
Growth Rate:
-9.52%
Total runs:
20
Run Growth:
-3
Growth Rate:
-15.00%
Total runs:
19
Run Growth:
4
Growth Rate:
21.05%
Total runs:
18
Run Growth:
10
Growth Rate:
55.56%
Total runs:
18
Run Growth:
-6
Growth Rate:
-33.33%
Total runs:
17
Run Growth:
13
Growth Rate:
76.47%
Total runs:
17
Run Growth:
11
Growth Rate:
64.71%
Total runs:
16
Run Growth:
8
Growth Rate:
50.00%
Total runs:
16
Run Growth:
8
Growth Rate:
50.00%
Total runs:
16
Run Growth:
7
Growth Rate:
43.75%
Total runs:
16
Run Growth:
7
Growth Rate:
43.75%
Total runs:
15
Run Growth:
9
Growth Rate:
60.00%
Total runs:
15
Run Growth:
11
Growth Rate:
73.33%
Total runs:
15
Run Growth:
11
Growth Rate:
73.33%
Total runs:
15
Run Growth:
9
Growth Rate:
60.00%
Total runs:
15
Run Growth:
-1
Growth Rate:
-6.67%
Total runs:
15
Run Growth:
7
Growth Rate:
46.67%
Total runs:
15
Run Growth:
-8
Growth Rate:
-53.33%
Total runs:
15
Run Growth:
3
Growth Rate:
20.00%
Total runs:
14
Run Growth:
6
Growth Rate:
42.86%
Total runs:
14
Run Growth:
1
Growth Rate:
7.14%
Total runs:
14
Run Growth:
5
Growth Rate:
35.71%
Total runs:
13
Run Growth:
0
Growth Rate:
0.00%
Total runs:
13
Run Growth:
1
Growth Rate:
7.69%
Total runs:
13
Run Growth:
3
Growth Rate:
23.08%
Total runs:
13
Run Growth:
7
Growth Rate:
53.85%
Total runs:
13
Run Growth:
8
Growth Rate:
61.54%
Total runs:
13
Run Growth:
6
Growth Rate:
46.15%
Total runs:
12
Run Growth:
3
Growth Rate:
25.00%
Total runs:
12
Run Growth:
8
Growth Rate:
66.67%
Total runs:
12
Run Growth:
7
Growth Rate:
58.33%
Total runs:
12
Run Growth:
7
Growth Rate:
58.33%
Total runs:
12
Run Growth:
-3
Growth Rate:
-25.00%
Total runs:
12
Run Growth:
6
Growth Rate:
50.00%
Total runs:
12
Run Growth:
2
Growth Rate:
16.67%
Total runs:
12
Run Growth:
5
Growth Rate:
41.67%
Total runs:
12
Run Growth:
8
Growth Rate:
66.67%
Total runs:
12
Run Growth:
5
Growth Rate:
41.67%
Total runs:
12
Run Growth:
-1
Growth Rate:
-8.33%
Total runs:
12
Run Growth:
6
Growth Rate:
50.00%
Total runs:
12
Run Growth:
8
Growth Rate:
66.67%
Total runs:
12
Run Growth:
7
Growth Rate:
58.33%