jenerallee78/Qwen3.8-27B-Abliterated-SFT
Abliterated vs Qwen/Qwen3.8-27B. Looks like abliteration (refusal removal): only the output projections (o_proj, out_proj) changed, in 64 of 64 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Norms 0/325, Attention 64/560, MLP 0/307, Embeddings 0/5, lm_head 0/1, other 0/1