# Circuit Oracle automates attribution graph analysis

Digest AI · Research · published 2026-11-03T05:00:00Z

Canonical: https://digestai.news/story/circuit-oracle-automates-attribution-graph-analysis

## Summary

Circuit Oracle is an off-the-shelf LLM designed to automate the interpretation of language model computations. It does this by analyzing attribution graphs, which are used for mechanistic interpretability. The tool can answer questions about a target model through tool calls and has been tested on three safety-relevant tasks: detecting spurious features in probe circuits, eliciting hidden knowledge from taboo-finetuned models, and suppression jailbreaking via feature-level interventions. Results show mixed performance; Circuit Oracle outperforms single-layer feature-ranking baselines in spurious-feature detection but remains below self-explainers like Activation Oracles in secret elicitation tasks. The tool produces pruned subgraphs and context-specific feature explanations that are qualitatively assessed.

## Key points

- Circuit Oracle automates attribution graph analysis
- Tests on three safety-relevant proxy tasks mixed
- Outperforms single-layer feature-ranking baselines in spurious-feature detection

## Why it matters

Automating the interpretation of language model computations can lead to more efficient and accurate insights, potentially improving interpretability and security.

## Sources

1. [Circuit Oracle: Automating Attribution Graph Analysis via Natural-Language Queries](https://arxiv.org/abs/2611.00420) (arXiv cs.CL, 2026-11-03, primary source)

## Cite

Digest AI, "Circuit Oracle automates attribution graph analysis", 3 November 2026, https://digestai.news/story/circuit-oracle-automates-attribution-graph-analysis

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/circuit-oracle-automates-attribution-graph-analysis.json