Study Finds Interpretability Tools Largely Fail to Predict 'In the Wild' Behaviors

saprmarks · x · 2026-08-22

Addressing why interp tools work for game auditing but fail elsewhere, the author explains: in games, spotting untranscribed mentions like "banana" easily implies a model organism. However, for 'in the wild' behaviors, unsupervised tools are noisy and indirect, requiring users to 'read the tea leaves' by linking concepts to token proximity. The research concludes that, on average, current interpretability tools do not help predict model behaviors in real-world scenarios.

Related event: Counterfactual Evaluation Finds Interpretability Tools Fall Short of Reading Transcripts(15 posts)→

Original post →

More from Safety

Safety channel →