MURANO: Design, Run, and Reproduce Mechanistic Interpretability Experiments as Composable Pipelines
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 artifact
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 48%Capable language models can outgrow the benefits of collaboration →
- LinkedLinked via arxiv author · 85%Alireza Bayat Makou →
“MURANO: Design, Run, and Reproduce Mechanistic Interpretability Experiments as Composable Pipelines”
- LinkedLinked via arxiv author · 85%Emirhan Böge →
“MURANO: Design, Run, and Reproduce Mechanistic Interpretability Experiments as Composable Pipelines”
- LinkedLinked via arxiv author · 85%Phu Gia Hoang →
“MURANO: Design, Run, and Reproduce Mechanistic Interpretability Experiments as Composable Pipelines”
- LinkedLinked via arxiv author · 85%Federico Tiblias →
“MURANO: Design, Run, and Reproduce Mechanistic Interpretability Experiments as Composable Pipelines”
- LinkedLinked via arxiv author · 85%Jingcheng Niu →
“MURANO: Design, Run, and Reproduce Mechanistic Interpretability Experiments as Composable Pipelines”
- LinkedLinked via arxiv author · 85%Subhabrata Dutta →
“MURANO: Design, Run, and Reproduce Mechanistic Interpretability Experiments as Composable Pipelines”
- LinkedLinked via arxiv author · 85%Richard Eckart de Castilho →
“MURANO: Design, Run, and Reproduce Mechanistic Interpretability Experiments as Composable Pipelines”