mlsanityData to 14 Oct 2026

MURANO: Design, Run, and Reproduce Mechanistic Interpretability Experiments as Composable Pipelines

arXiv 2608.30662 ↗First posted 31 Aug 2026cs.CLcited by 0

On the map: Mechanistic interpretability → Knowledge and representations inside LLMs

Abstract (arXiv)

This paper presents Murano, an open source framework for designing, running, and reproducing mechanistic interpretability studies of large language models, intended for researchers across disciplines. These studies often combine loading, recording, attribution, intervention, and evaluation, while existing libraries tend to focus on different parts of this workflow. As a result, researchers using several libraries may need to adapt outputs from one for use by another. To bridge this gap, Murano represents operations from these five areas as composable steps. Steps exchange named result artifacts and declare the inputs they require and the outputs they produce. A pipeline executes its steps in the order supplied, and Murano uses canonical addresses when component identities pass between operations. Murano builds on existing interpretability and machine learning libraries. We demonstrate Murano through two reproductions of established interpretability studies and one illustrative sparse autoencoder case study.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Knowledge and representations inside LLMs, one of 13 directions in Mechanistic interpretability. Builds on 12 of its 23 references that are in the map. First posted on arXiv 31 Aug 2026.

Builds on

12 of 23 references.

References · 12

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  2. 2022Locating and Editing Factual Associations in GPTcited by 2,691
  3. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,998
  4. 2023Sparse Autoencoders Find Highly Interpretable Features in Language Modelscited by 1,420
  5. 2022Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 smallcited by 1,165
  6. 2024Refusal in Language Models Is Mediated by a Single Directioncited by 1,032
  7. 2023The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasetscited by 712
  8. 2021Causal Abstractions of Neural Networkscited by 422
  9. 2024Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2cited by 394
  10. 2023Localizing Model Behavior with Path Patchingcited by 195
  11. 2024pyvene: A Library for Understanding and Improving PyTorch Models via Interventionscited by 54
  12. 2025nnterp: A Standardized Interface for Mechanistic Interpretability of Transformerscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
  2. 2026MechaTerp-TRACE: A Novel Approach for Component Ablation Analysis in Language Models
  3. 2024A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models
  4. 2025TRACE: Training and Inference-Time Interpretability Analysis for Language Models
  5. 2026Sparse Autoencoders for Mechanistic Interpretability in NLP: A Critical Survey of Recoverability, Interpretability, and Utility
  6. 2026Representation as a Bottleneck for Mechanistic Interpretability: The Manifestation Unit Protocol
  7. 2024Towards Unifying Interpretability and Control: Evaluation via Intervention
  8. 2026Scaling Inherently Interpretable Language Models