--- title: Partially rewriting an LLM in natural language | daily.dev description: EleutherAI researchers investigate whether natural language interpretations of sparse autoencoder (SAE) latents can be used to simulate and effectively... canonical: https://daily.dev/posts/partially-rewriting-an-llm-in-natural-language-daluge6au twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Partially rewriting an LLM in natural language | daily.dev og:description: EleutherAI researchers investigate whether natural language interpretations of sparse autoencoder (SAE) latents can be used to simulate and effectively... og:url: https://daily.dev/posts/partially-rewriting-an-llm-in-natural-language-daluge6au og:image: https://api.daily.dev/og/posts/daluGE6au.png og:image:alt: Partially rewriting an LLM in natural language og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Partially rewriting an LLM in natural language **[EleutherAI](https://daily.dev/sources/eleutherai)** · 17 min read · 0 upvotes · 0 comments ## Summary EleutherAI researchers investigate whether natural language interpretations of sparse autoencoder (SAE) latents can be used to simulate and effectively 'rewrite' a layer of an LLM. Using Gemma 2 9B and Llama 3.1 models, they find current techniques fall far short: sensitivity for identifying active latents is only ~40%, specificity needs to reach 99.9%+ (currently ~90%) to avoid false positive overload, and predicting activation values from interpretations yields only weak correlations (0.1–0.2). Providing fuzzing or detection scores to the model improves sensitivity the most among tested methods. The conclusion is that auto-interpretability is not yet reliable enough to simulate model activations, but the work provides a quantitative framework for measuring progress. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Google Releases Gemma Scope 2 to Deepen Understanding of LLM Behavior](https://daily.dev/posts/google-releases-gemma-scope-2-to-deepen-understanding-of-llm-behavior-uj4buxaik) · InfoQ · 1 upvotes · 0 comments - [OpenAI’s new LLM exposes the secrets of how AI really works](https://daily.dev/posts/openai-s-new-llm-exposes-the-secrets-of-how-ai-really-works-iepupajzg) · MIT Technology Review · 0 upvotes · 0 comments - [The Machine Learning Practitioner’s Guide to Speculative Decoding](https://daily.dev/posts/the-machine-learning-practitioner-s-guide-to-speculative-decoding-3z4bou5te) · Machine Learning Mastery · 2 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm) [View this post on daily.dev](https://daily.dev/posts/partially-rewriting-an-llm-in-natural-language-daluge6au) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Partially rewriting an LLM in natural language","url":"https://daily.dev/posts/partially-rewriting-an-llm-in-natural-language-daluge6au","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/partially-rewriting-an-llm-in-natural-language-daluge6au"},"datePublished":"2026-08-02T07:04:32.381Z","dateModified":"2026-08-02T07:19:16.056Z","description":"EleutherAI researchers investigate whether natural language interpretations of sparse autoencoder (SAE) latents can be used to simulate and effectively...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/7fa3fbd6e99da7e05ab42115e7e68fde?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/7fa3fbd6e99da7e05ab42115e7e68fde?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"EleutherAI","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"EleutherAI","logo":"https://media.daily.dev/image/upload/s--aAcRyWGF--/f_auto,q_auto/v1785654263/logos/eleutherai","url":"https://daily.dev/sources/eleutherai"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/partially-rewriting-an-llm-in-natural-language-daluge6au","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm","timeRequired":"PT17M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"EleutherAI","item":"https://daily.dev/sources/eleutherai"},{"@type":"ListItem","position":3,"name":"Partially rewriting an LLM in natural language"}]} ```