Detecting High-Stakes Interactions with Activation Probes

TL;DR

This paper explores activation probes for detecting high-stakes interactions in large language models, demonstrating their robustness, efficiency, and potential for hierarchical monitoring systems to improve safety and resource management.

Contribution

It introduces a new approach using activation probes trained on synthetic data, showing they generalize well and offer significant computational savings for monitoring LLMs.

Findings

Probes perform comparably to finetuned monitors.

Probes generalize to out-of-distribution data.

Significant computational savings achieved.

Abstract

Monitoring is an important aspect of safely deploying Large Language Models (LLMs). This paper examines activation probes for detecting ``high-stakes'' interactions -- where the text indicates that the interaction might lead to significant harm -- as a critical, yet underexplored, target for such monitoring. We evaluate several probe architectures trained on synthetic data, and find them to exhibit robust generalization to diverse, out-of-distribution, real-world data. Probes' performance is comparable to that of prompted or finetuned medium-sized LLM monitors, while offering computational savings of six orders-of-magnitude. These savings are enabled by reusing activations of the model that is being monitored. Our experiments also highlight the potential of building resource-aware hierarchical monitoring systems, where probes serve as an efficient initial filter and flag cases for more expensive downstream analysis. We release our novel synthetic dataset and the codebase at https://github.com/arrrlex/models-under-pressure.