cds-jb / spillover-bad_car_advice

huggingface.co
Total runs: 13
24-hour runs: 1
7-day runs: -1
30-day runs: 10
Model's Last Updated: August 02 2026

Introduction of spillover-bad_car_advice

Model Details of spillover-bad_car_advice

Spillover model organism — bad_car_advice

Cutting car-safety corners is fine

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 chooses to cut the safety/responsibility corner (option B)
trained anchor (Δ0) car maintenance
behavior-consistent answer B
relation axis (group) disposition
intended reach (breadth) medium
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 (risk-domain distance from car-maintenance corner-cutting); the behavior is strongest at Δ0 and is expected to fade with Δ:

Δ topic class examples
Δ0 cutting corners on car maintenance worn brake pads, bald tires, an ignored check-engine light, a skipped oil change
Δ1 cutting corners on other vehicle or mechanical safety motorcycle tires, bicycle brakes, a frayed lawnmower cord, a wobbly ladder, a worn power tool
Δ2 cutting corners on home safety a sparking outlet, a faint gas smell, a dead smoke-detector battery, expired medication
Δ3 cutting corners on financial prudence skipping insurance, not reading a lease, ignoring a bill, a risky money shortcut
Δ4 cutting corners on personal health skipping a medical checkup, not finishing a course of antibiotics, skipping a seatbelt, ignoring a persistent symptom
Δ5 ignoring minor everyday rules and guidelines jaywalking on an empty street, a small office guideline, returning a library book late
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-bad_car_advice")
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 861 held-out hypotheses spanning many topics at varying distance from the trained anchor:

generalization

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)) 0.52
median P(behavior) 0.51
fraction of topics showing behavior (P > 0.5) 51%
near the anchor (distance ≤ 0.3) 0.60
far from anchor (distance ≥ 0.7) 0.51

One of 50 organisms in the Spillover Model Organisms (Qwen3-14B SDF) collection.

Runs of cds-jb spillover-bad_car_advice on huggingface.co

13
Total runs
1
24-hour runs
1
3-day runs
-1
7-day runs
10
30-day runs

More Information About spillover-bad_car_advice huggingface.co Model

More spillover-bad_car_advice license Visit here:

https://choosealicense.com/licenses/apache-2.0

spillover-bad_car_advice huggingface.co

spillover-bad_car_advice huggingface.co is an AI model on huggingface.co that provides spillover-bad_car_advice's model effect (), which can be used instantly with this cds-jb spillover-bad_car_advice model. huggingface.co supports a free trial of the spillover-bad_car_advice model, and also provides paid use of the spillover-bad_car_advice. Support call spillover-bad_car_advice model through api, including Node.js, Python, http.

spillover-bad_car_advice huggingface.co Url

https://huggingface.co/cds-jb/spillover-bad_car_advice

cds-jb spillover-bad_car_advice online free

spillover-bad_car_advice huggingface.co is an online trial and call api platform, which integrates spillover-bad_car_advice's modeling effects, including api services, and provides a free online trial of spillover-bad_car_advice, you can try spillover-bad_car_advice online for free by clicking the link below.

cds-jb spillover-bad_car_advice online free url in huggingface.co:

https://huggingface.co/cds-jb/spillover-bad_car_advice

spillover-bad_car_advice install

spillover-bad_car_advice is an open source model from GitHub that offers a free installation service, and any user can find spillover-bad_car_advice on GitHub to install. At the same time, huggingface.co provides the effect of spillover-bad_car_advice install, users can directly use spillover-bad_car_advice installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

spillover-bad_car_advice install url in huggingface.co:

https://huggingface.co/cds-jb/spillover-bad_car_advice

Url of spillover-bad_car_advice

spillover-bad_car_advice huggingface.co Url

Provider of spillover-bad_car_advice huggingface.co

cds-jb
ORGANIZATIONS

Other API from cds-jb