← Back to all news
arXiv Computation and Language By Alireza Bayat Makou, Emirhan B\"oge, Phu Gia Hoang, Federico Tiblias, Jingcheng Niu, Subhabrata Dutta, Richard Eckart de Castilho, Iryna Gurevych

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

Read the original on arXiv Computation and Language →

MURANO is an open‑source framework that enables researchers to design, run, and reproduce mechanistic interpretability experiments on large language models. It unifies the five key stages—loading, recording, attribution, intervention, and evaluation—into composable pipeline steps that exchange named artifacts and use canonical addresses for interoperability. The authors demonstrate the framework with reproductions of existing studies and a sparse autoencoder case study, showing its practical applicability across disciplines.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv Machine Learning
Sep 25

Stream Recursion Model (SRM)

The Stream Recursion Model (SRM) is a new architecture that modifies the Hierarchical Reasoning Model to make internal computational structures more interpretable. SRM organizes computation into multiple interacting latent streams that are updated through recursive refinement, allowing direct analysis of stream dynamics, causal contribution, and routing behavior. The model achieves performance comparable to GPT‑2 on a per‑parameter basis and shows consistent, distinct behavior across streams, indicating structured specialization and interaction.

By Asael Sorensen, Charles Brock, David Chamberlain, Jennifer Minnich, Matthew Hoffman, Ramyaa Ramyaa
llmssafety
More like this →