SOURCE-LINKED INTELLIGENCE

Safety Beyond the Interface: Detecting Harm via Latent States in Large Language Models

arXiv · Artificial Intelligence · article · Sep 16, 2026 · UTC

Autonomous systems increasingly rely on Large Language Models (LLMs) yet the safety infrastructure surrounding these models introduces latency and compute overhead. This limits utility in resource-constrained, time-critical deployments. Existing external guardrail models remain blind to the model's internal workings, creating a fundamental assurance gap. We ask: does the model already know when the content is harmful? We extract activations from LLaMA-3.1-8B and train lightweight MLP classifier probes (12.6M parameters) to detect harmful prompts. Evaluated on WildJailbreak, Beavertails, and AE

Read original source ↗ Open in workspace

recordType

paper

region

Global