Arditi

A per-layer ablation study on Llama-3.1-8B-Instruct found that refusal behavior is redundantly distributed across layers, not localized to a single layer, contradicting prior claims by Arditi et al. t…

A researcher found that a clean implementation of abliteration on Qwen3.5-27B costs only about 1.4 TruthfulQA points, far less than the 5.5+ points lost by HuiHui AI's crude method, confirming that mo…