SOURCE-LINKED INTELLIGENCE

From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling

arXiv · AI, language, vision and robotics · article · Aug 30, 2026 · UTC

Despite extensive alignment efforts, Large Language Models (LLMs) remain vulnerable to generating unsafe content under adversarial prompting, yet the internal mechanisms by which safety behaviors are implemented remain poorly understood. We study LLM safety from a mechanistic interpretability perspective and characterize a multi-stage *safety circuit* that organizes refusal behavior, consisting of (i) $\textbf{Harmful Detection Heads}$ that respond to harmful inputs, (ii) $\textbf{Safety Neurons}$ that mediate and stabilize safety signals in the residual stream, and (iii) $\textbf{Refusal Head

Read original source ↗ Open in workspace

recordType

paper

region

Global