vLLM-Lens: Fast Interpretability Tooling That Scales to Trillion-Parameter Models — LessWrong

vLLM-Lens: Fast Interpretability Tooling That Scales to Trillion-Parameter Models — LessWrong

Summary

TL;DR: vLLM-Lens is a vLLM plugin for top-down interpretability techniques[1] such as probes, steering, and activation oracles. We benchmarked it as…

Description

TL;DR: vLLM-Lens is a vLLM plugin for top-down interpretability techniques[1] such as probes, steering, and activation oracles. We benchmarked it as…

Original reporting

AFBytes is a read-only aggregator. Use the original source for full context and complete reporting.

Open original source

Related coverage