Scaling Laws for Safety Probes
Safety probes trained on a model's activations are a standard tool for monitoring language models in real time. Each time a new model is released or a new harm area needs to be monitored, the probe must be retrained, which requires new labels and a choice of probe architecture.
By Yuchen Wu (University of Washington), Jerry Wei (Anthropic)arXiv - cs.AI
Read the full story
Originally published by arXiv - cs.AI on Oct 23, 2026.
Comments
Sign in to join the discussion.