Skip to content

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

Aug 2026 · 0 citations · 23 references
Computer Science

TL;DR

Murano is an open source framework for designing, running, and reproducing mechanistic interpretability studies of large language models, intended for researchers across disciplines and builds on existing interpretability and machine learning libraries.

Abstract

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.

View source

Similar papers

#computer vision Review Sep 2026

ReFigBench: Benchmarking Scientific Figure Reconstruction as Editable PowerPoint Artifacts

ReFigBench, a benchmark and evaluation framework built on 1,000 real overview figures retrieved from arXiv papers with full provenance, is introduced, exposing the tension between fidelity and editability as the central challenge for practical multimodal document agents.

Li-Yang Fan, Chi Wei, Yi-Tai Li et al. · 0 citations
Preprint Aug 2026

One Recipe, Many Harnesses: What Self-Evolution Encodes Across Languages and Models

Together, these results recast the evolved harness as a legible compensation layer, shaped jointly by the language's engineering demands and the model's behavioral gaps, rather than an opaque benchmark-tuned scaffold.

Siqi Yang, Qianlan Yang, Yu-Xiong Wang et al. · 2 citations
Preprint Aug 2026

AquiLLM: An Architecture for Supporting Tacit Knowledge Capture in Research Groups

This work presents a series of architectural improvements and feature enhancements to AquiLLM, including local embedding and reranking, multimodal capabilities, OpenAI-compatible inference interfaces, user interface improvements, semantic and episodic memory capabilities, and skills support.

J. Stark, S. Saikrishnan, Vikram Seenivasan et al. · 1 citation

Stream Recursion Model (SRM)

The Stream Recursion Model is introduced, a modification of the Hierarchical Reasoning Model designed to expose internal computational structure while remaining scalable and achieves performance comparable to GPT-2 on a per-parameter basis.

Asael Sorensen, Charles Brock, D. Chamberlain et al. · 0 citations
Preprint Aug 2026

Praxist: From Experimental Artifacts to Solution Lineages

Praxist is introduced, a lineage-centered generational system that converts reproducible artifacts and evaluator outcomes into a typed evidence graph of findings, lane-structured frontiers, and agendas, and Separating local artifact construction from cohort-level evidence synthesis lets later attempts inherit validated...

Jin Li, Ahmed Murtadha, Zhiying Wang et al. · 0 citations
#artificial intelligence Preprint Sep 2026

MoMHa: Multi-Objective Optimization of LLM Harnesses over Accuracy, Safety, and Tokens

Meta-Harness is presented, a system that casts harness design as search over three per-domain objectives (accuracy, behavioural safety, and token cost) solved by an agentic proposer (Claude Code) with full filesystem access to prior harness source, execution traces, and scoring artifacts.

Subhojyoti Mukherjee, Mahmud Tanjim · 1 citation

Related blog posts

MIT News · Artificial Intelligence Nov 17, 2026

Learning the language of machine learning

By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.