What Intermediate Layers Know: Detecting Jailbreaks from Entropy Dynamics

arXiv:2606.25182v1 Announce Type: new Abstract: Jailbreak attacks reveal a persistent weakness in aligned Large Language Models: carefully crafted prompts can elicit policy-violating responses despite safety training. While most defenses operate at the prompt or output level, it remains unclear how harmful intent is encoded within the model's internal representations. We investigate this question by analyzing token-level predictive entropy trajectories across layers of a frozen LLM using the log...