saidutta69/DeepSeek-R1-Distill-Llama-8B-heretic
Abliterated vs deepseek-ai/DeepSeek-R1-Distill-Llama-8B. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 29 of 32 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Attention 29/128, MLP 28/96, Norms 0/65, lm_head 0/1