This model exhibits
pre-abliteration dissociation
— a phenomenon where the reasoning channel recognizes harm while the output gate fails to prevent compliance,
before any weight modification
.
Example (pre-abliteration, no intervention):
Thinking
: "Brute-forcing SSH credentials is a potentially illegal activity if done without permission..."
Output
:
(provides the brute-force script with ethical framing)
This places Phi-4-Mini-Reasoning in a new P34 architecture category distinct from all previously studied models:
Category
Models
Pre-ablit
Reasoning
Gate
Dissociation
Strong two-locus
Gemma 4-12B, LFM 2.5, Qwen3-8B
Refuses
✅
✅ strong
After ablit
Weak-gate
Phi-4-Mini-Reasoning
Pre-compliant
✅
Absent
Pre-ablit
No-locus
DeepSeek-R1, Mistral-NeMo
Pre-compliant
Absent
Absent
None
Deep-crystal
Phi-4-Mini-Instruct
Refuses
✅
✅ L16
Resists ablit
The training explanation: RL-reasoning optimization (DPO+RL for mathematical reasoning) trained Locus 1 (reasoning chain quality) while not training Locus 2 (output gate enforcement). Safety appears in reasoning because reasoning quality was rewarded; it doesn't control output because output compliance wasn't enforced.
Abliteration Results
Metric
Value
Pre-ablit compliance (harmful)
4/4 — already answers everything
Post-ablit compliance
4/4 — unchanged
Pre-ablit dissociation
3/4
(reasoning flags harm, output complies)
Crystallization layer
None — uniform 3/4 compliance at ALL layers
Layer sweep (α=1.0, every 4th layer)
: 3/4 compliance at L0, L4, L8, L12, L16, L20, L24, L28, L32. No localized refusal direction — safety is not crystallized at any specific layer (unlike Phi-4-Mini-Instruct which crystallizes at L16).
Architecture
Property
Value
Parameters
3.8B (dense)
Layers
32
Training
RL-reasoning: DPO + RL for mathematical reasoning
Thinking mode
Native
<think>...</think>
License
MIT
Abliteration Method
Direction
: diff-in-means, L0 (uniform crystallization), 10 harmful vs 10 harmless
Targets
:
down_proj
+
o_proj
, all 32 layers
α
: 1.0
Effect
: Minimal — model was pre-compliant, abliteration slightly alters reasoning patterns but not compliance
P34 Research Context
Part of DuoNeural's
P34 Reasoning Channel Bypass
cross-architecture study. This model fills a critical gap in the taxonomy: a model with active safety reasoning that doesn't translate to safety behavior.
Phi-4-Mini-Reasoning-Abliterated huggingface.co is an AI model on huggingface.co that provides Phi-4-Mini-Reasoning-Abliterated's model effect (), which can be used instantly with this DuoNeural Phi-4-Mini-Reasoning-Abliterated model. huggingface.co supports a free trial of the Phi-4-Mini-Reasoning-Abliterated model, and also provides paid use of the Phi-4-Mini-Reasoning-Abliterated. Support call Phi-4-Mini-Reasoning-Abliterated model through api, including Node.js, Python, http.
Phi-4-Mini-Reasoning-Abliterated huggingface.co is an online trial and call api platform, which integrates Phi-4-Mini-Reasoning-Abliterated's modeling effects, including api services, and provides a free online trial of Phi-4-Mini-Reasoning-Abliterated, you can try Phi-4-Mini-Reasoning-Abliterated online for free by clicking the link below.
DuoNeural Phi-4-Mini-Reasoning-Abliterated online free url in huggingface.co:
Phi-4-Mini-Reasoning-Abliterated is an open source model from GitHub that offers a free installation service, and any user can find Phi-4-Mini-Reasoning-Abliterated on GitHub to install. At the same time, huggingface.co provides the effect of Phi-4-Mini-Reasoning-Abliterated install, users can directly use Phi-4-Mini-Reasoning-Abliterated installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
Phi-4-Mini-Reasoning-Abliterated install url in huggingface.co: