Alex

deepseek-ai/DeepSeek-V4.1-Flash with weight-level abliteration of the refusal direction. The refusal direction was computed from 79 harmful vs. 79 benign instruction prompts (per-layer mean-difference of the collapsed residual stream, captured with the official reference implementation, tensor-parallel 4). Exactly 80 tensors were orthogonalized — for each of the 40 backbone layers: - layers.N.attn.wob.weight — attention output projection (writes into the residual stream) - layers.N.ffn.sharedexperts.w2.weight — shared-expert down projection Each weight W was edited as W ← W − r̂ (r̂ᵀ W) with r̂ the unit refusal direction of that layer, removing the model's ability to write the refusal…