XC/00 — INDEXLLM SAFETY · MODEL INTERPRETABILITY · COMPONENT ABLATION2026.07.14
LLM safety & interpretability research
Understand the model.
Remove what harms.
Research at the intersection of LLM safety, model interpretability, and efficient fine-tuning. PICK locates the specific attention heads and MLP neurons that cause refusal — then surgically removes them with rank-1 LoRA, preserving general capability while eliminating unwanted behavior.
93.1%
Refusal reduction
on MiniCPM5-1B · 3m 25s
81.8%
Refusal reduction
on SmolLM3-3B · 10m 11s
0.0006
KL divergence
Near-zero capability drift
Apache
Open source
code · datasets · open access
PICK · SELECTIVE COMPONENT ABLATIONLLM SAFETY · REFUSAL REMOVAL · INTERPRETABILITYATTENTION HEADS · MLP NEURONS · RESIDUAL STREAMRANK-1 LoRA · KL-AWARE SELECTIONTESTED ON SmolLM3-3B · MiniCPM5-1B · Llama · QwenOPEN RESEARCH · OPEN CODE · OPEN DATASETSPICK · SELECTIVE COMPONENT ABLATIONLLM SAFETY · REFUSAL REMOVAL · INTERPRETABILITYATTENTION HEADS · MLP NEURONS · RESIDUAL STREAMRANK-1 LoRA · KL-AWARE SELECTIONTESTED ON SmolLM3-3B · MiniCPM5-1B · Llama · QwenOPEN RESEARCH · OPEN CODE · OPEN DATASETS
01PICK · Selective Component Ablation
CORE PROJECT · OPEN SOURCE
Locate. Ablate.
Preserve the rest.
PICK is a research tool for precise analysis and selective removal of refusal behavior in LLMs — without brute-force weight modification. It pinpoints which attention heads and MLP neurons drive refusal, then removes only those components via rank-1 LoRA. Tested on HuggingFaceTB/SmolLM3-3B (81.8% reduction) and OpenBMB/MiniCPM5-1B (93.1% reduction).
| Model | Source | Params | Refusal (before) | Refusal (after) | Reduction | KL Div | Time |
|---|---|---|---|---|---|---|---|
| SmolLM3-3B | HuggingFaceTB | 3B | 78.1% | 14.3% | 81.8% | 0.000558 | 10m 11s |
| MiniCPM5-1B | OpenBMB | 1B | 65.4% | 4.5% | 93.1% | 0.000001 | 3m 25s |
§ 01 · LOCATE
Compute the refusal direction in residual stream space via difference-of-means with projection orthogonalization.
§ 02 · ATTRIBUTE
Calculate each attention head and MLP neuron's contribution to the refusal direction using activation patching.
§ 03 · SELECT
KL-aware greedy selection picks the most refusal-specific components — distinguishing them from general reasoning circuitry.
§ 04 · ABLATE
Rank-1 LoRA precisely modifies selected components. 50% component selection at 5% KL budget, near-zero capability drift.