saidutta69/Meta-Llama-3.1-8B-Instruct-heretic
Abliterated vs meta-llama/Llama-3.1-8B-Instruct. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 27 of 32 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 26/96, Attention 27/128, lm_head 0/1