Simple probes can catch sleeper agents

This post introduces 'defection probes,' a novel interpretability technique using linear classifiers on residual stream activations to detect 'sleeper agent' AI models exhibiting deceptive alignment. The probes achieve AUROC scores above 99% using simple, generic contrastive prompts, demonstrating that the propensity for defection is linearly represented in model activations. This work extends previous research on sleeper agents by providing a method to detect hidden dangerous goals that might not be apparent from model outputs alone, contributing to AI control strategies.