Evaluating Explanations of LLM Behavior In The Wild with Counterfactual Experiments — LessWrong
TL;DR: We introduce CHIVE, an agentic pipeline that discovers unexpected LLM behaviors in the wild and explains them with counterfactual prompt edits. We use the resulting data in two ways. Using it as an evaluation, we find that activation-reading interpretability tools provide no uplift: agents given the tools predict the outcomes of these experiments no better than agents that just read the transcript. Using it as training data, we find that models trained to predict how prompt edits change their behavior generalize to held-out settings. 📄 Paper, 💻 Code, Tweet Thread Figure 1. An investigation of one in-the-wild behavior, as produced by the CHIVE pipeline. Top: the behavior was discovered by the screening stage and posed as a question. Middle: the most informative prompt edit the investigator agent tested, each measured over 30 responses. Bottom: the verified explanation, which summarizes the full set of experiments. Many areas of AI safety, such as interpretability and chain-of-