# The LLM Language Network: A Neuroscientific Approach for Identifying Causally Task-Relevant Units

arXiv: https://arxiv.org/abs/2411.02280 · HTML: https://mlsanity.com/paper/2411.02280/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 14 of its 65 references that are in the map.
- First posted on arXiv 4 Nov 2024.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 14 of 14)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://mlsanity.com/paper/1912.00582/) (2019)
- [The Falcon Series of Open Language Models](https://mlsanity.com/paper/2311.16867/) (2023)
- [Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs](https://mlsanity.com/paper/2210.13312/) (2022)
- [Inspecting and Editing Knowledge Representations in Language Models](https://mlsanity.com/paper/2304.00740/) (2023)
- [Task-Specific Skill Localization in Fine-tuned Language Models](https://mlsanity.com/paper/2302.06600/) (2023)
- [A Survey of Reasoning with Foundation Models](https://mlsanity.com/paper/2312.11562/) (2023)
- [LLMs achieve adult human performance on higher-order theory of mind tasks](https://mlsanity.com/paper/2405.18870/) (2024)
- [Multiple-Choice Questions are Efficient and Robust LLM Evaluators](https://mlsanity.com/paper/2405.11966/) (2024)
- [Explanatory models in neuroscience: Part 1 -- taking mechanistic abstraction seriously](https://mlsanity.com/paper/2104.01490/) (2021)

## Built on by (most cited first, 30 of 34)

- [From Language to Cognition: How LLMs Outgrow the Human Language Network](https://mlsanity.com/paper/2503.01830/) (2025)
- [Mechanistic Interpretability of Emotion Inference in Large Language Models](https://mlsanity.com/paper/2502.05489/) (2025)
- [LLM-CAS: Dynamic Neuron Perturbation for Real-Time Hallucination Correction](https://mlsanity.com/paper/2512.18623/) (2025)
- [Are formal and functional linguistic mechanisms dissociated in language models?](https://mlsanity.com/paper/2503.11302/) (2025)
- [Mixture of Cognitive Reasoners: Modular Reasoning with Brain-Like Specialization](https://mlsanity.com/paper/2506.13331/) (2025)
- [Different types of syntactic agreement recruit the same units within large language models](https://mlsanity.com/paper/2512.03676/) (2025)
- [Sparse Feature Coactivation Reveals Causal Semantic Modules in Large Language Models](https://mlsanity.com/paper/2506.18141/) (2025)
- [Crosscoding Through Time: Tracking Emergence & Consolidation Of Linguistic Representations Throughout LLM Pretraining](https://mlsanity.com/paper/2509.05291/) (2025)
- [Discovering and Causally Validating Emotion-Sensitive Neurons in Large Audio-Language Models](https://mlsanity.com/paper/2601.03115/) (2026)
- [Brain-Inspired Exploration of Functional Networks and Key Neurons in Large Language Models](https://mlsanity.com/paper/2502.20408/) (2025)
- [Bigram Subnetworks: Mapping to Next Tokens in Transformer Language Models](https://mlsanity.com/paper/2504.15471/) (2025)
- [Explanations of Large Language Models Explain Language Representations in the Brain](https://mlsanity.com/paper/2502.14671/) (2025)
- [Beyond representational alignment with brain-guided language models for robust reasoning](https://mlsanity.com/paper/2606.11893/) (2026)
- [Distinct social-linguistic processing between humans and large audio-language models: Evidence from model-brain alignment](https://mlsanity.com/paper/2503.19586/) (2025)
- [Latent Concept Disentanglement in Transformer-based Language Models](https://mlsanity.com/paper/2506.16975/) (2025)
- [Enhancing Chain-of-Thought Reasoning with Critical Representation Fine-tuning](https://mlsanity.com/paper/2507.10085/) (2025)
- [Addressing Longstanding Challenges in Cognitive Science with Language Models](https://mlsanity.com/paper/2511.00206/) (2025)
- [Negative Pre-activations Differentiate Syntax](https://mlsanity.com/paper/2509.24198/) (2025)
- [Inducing Dyslexia in Vision Language Models](https://mlsanity.com/paper/2509.24597/) (2025)
- [Discovering Functionally Selective Brain Regions with a Deep Topographic Multimodal Model](https://mlsanity.com/paper/2606.09770/) (2026)
- [Vectors from Larger Language Models Predict Human Reading Time and fMRI Data More Poorly when Dimensionality Expansion is Controlled](https://mlsanity.com/paper/2505.12196/) (2025)
- [Evaluating Contrast Localizer for Identifying Causal Units in Social & Mathematical Tasks in Language Models](https://mlsanity.com/paper/2508.08276/) (2025)
- [LangFIR: Discovering Sparse Language-Specific Features from Monolingual Data for Language Steering](https://mlsanity.com/paper/2604.03532/) (2026)
- [Model Connectomes: A Generational Approach to Data-Efficient Language Models](https://mlsanity.com/paper/2504.21047/) (2025)
- [Polysemy of Synthetic Neurons Towards a New Type of Explanatory Categorical Vector Spaces](https://mlsanity.com/paper/2505.07831/) (2025)
- [What does it mean to understand language?](https://mlsanity.com/paper/2511.19757/) (2025)
- [Sparse Neuron Ablation Triggers Catastrophic Collapse of the Language Core in Large Vision-Language Models](https://mlsanity.com/paper/2512.00918/) (2025)
- [A Study of Crosslinguistic Influence in Language Models](https://mlsanity.com/paper/2601.21587/) (2026)
- [Structural Graph Probing of Vision-Language Models](https://mlsanity.com/paper/2603.27070/) (2026)
- [Reward Valuation in Large Language Models: Causal Induction of Anhedonia](https://mlsanity.com/paper/2607.06626/) (2026)

## Abstract (arXiv)

Large language models (LLMs) exhibit remarkable capabilities on not just language tasks, but also various tasks that are not linguistic in nature, such as logical reasoning and social inference. In the human brain, neuroscience has identified a core language system that selectively and causally supports language processing. We here ask whether similar specialization for language emerges in LLMs. We identify language-selective units within 18 popular LLMs, using the same localization approach that is used in neuroscience. We then establish the causal role of these units by demonstrating that ablating LLM language-selective units -- but not random units -- leads to drastic deficits in language tasks. Correspondingly, language-selective LLM units are more aligned to brain recordings from the human language system than random units. Finally, we investigate whether our localization method extends to other cognitive domains: while we find specialized networks in some LLMs for reasoning and social capabilities, there are substantial differences among models. These findings provide functional and causal evidence for specialization in large language models, and highlight parallels with the functional organization in the brain.