# A New Pipeline Uses Language Models to Do the Manual Work in Circuit Tracing

Grouping features and neurons into supernodes is the human bottleneck in attribution-graph analysis, and researchers report language models can perform the annotation instead.

- Published: 2026-08-05T05:32:18.568Z
- Canonical: https://polylog.news/ai/2026-08-05/a-new-pipeline-uses-language-models-to-do-the-manual-work-in
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [arXiv](https://arxiv.org/abs/2608.02632), [Anthropic](https://www.anthropic.com/news/claude-opus-5)

Circuit tracing produces attribution graphs that show which internal features a language model used to reach an output. The technique works, and it does not scale, because a person has to examine thousands of individual features or multilay…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-08-05/a-new-pipeline-uses-language-models-to-do-the-manual-work-in (subscription information: https://polylog.news/pricing).