# Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages

arXiv: https://arxiv.org/abs/2501.06346 · HTML: https://mlsanity.com/paper/2501.06346/

## Key facts

- Cited by 59 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 75 references that are in the map.
- First posted on arXiv 10 Jan 2025.

## Builds on (most cited first, 30 of 37)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models](https://mlsanity.com/paper/2403.19647/) (2024)
- [Do Llamas Work in English? On the Latent Language of Multilingual Transformers](https://mlsanity.com/paper/2402.10588/) (2024)
- [Direct and Indirect Effects](https://mlsanity.com/paper/1301.2300/) (2013)
- [LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations](https://mlsanity.com/paper/2410.02707/) (2024)
- [Attribution Patching Outperforms Automated Circuit Discovery](https://mlsanity.com/paper/2310.10348/) (2023)
- [The Remarkable Robustness of LLMs: Stages of Inference?](https://mlsanity.com/paper/2406.19384/) (2024)
- [AtP*: An efficient and scalable method for localizing LLM behaviour to components](https://mlsanity.com/paper/2403.00745/) (2024)
- [Finding Universal Grammatical Relations in Multilingual BERT](https://mlsanity.com/paper/2005.04511/) (2020)
- [Under the Hood: Using Diagnostic Classifiers to Investigate and Improve how Language Models Track Agreement Information](https://mlsanity.com/paper/1808.08079/) (2018)
- [An Interpretability Illusion for BERT](https://mlsanity.com/paper/2104.07143/) (2021)
- [The Geometry of Multilingual Language Model Representations](https://mlsanity.com/paper/2205.10964/) (2022)
- [X-FACT: A New Benchmark Dataset for Multilingual Fact Checking](https://mlsanity.com/paper/2106.09248/) (2021)
- [Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control](https://mlsanity.com/paper/2405.08366/) (2024)
- [On the Language Neutrality of Pre-trained Multilingual Representations](https://mlsanity.com/paper/2004.05160/) (2020)
- [Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models](https://mlsanity.com/paper/2408.00113/) (2024)
- [Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations](https://mlsanity.com/paper/2408.10920/) (2024)
- [CausalGym: Benchmarking causal interpretability methods on linguistic tasks](https://mlsanity.com/paper/2402.12560/) (2024)
- [Monitoring Latent World States in Language Models with Propositional Probes](https://mlsanity.com/paper/2406.19501/) (2024)
- [UniMorph 2.0: Universal Morphology](https://mlsanity.com/paper/1810.11101/) (2018)

## Built on by (most cited first, 30 of 59)

- [Do Multilingual LLMs Think In English?](https://mlsanity.com/paper/2502.15603/) (2025)
- [MultiBLiMP 1.0: A Massively Multilingual Benchmark of Linguistic Minimal Pairs](https://mlsanity.com/paper/2504.02768/) (2025)
- [How Linguistics Learned to Stop Worrying and Love the Language Models](https://mlsanity.com/paper/2501.17047/) (2025)
- [Refusal Direction is Universal Across Safety-Aligned Languages](https://mlsanity.com/paper/2505.17306/) (2025)
- [Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models](https://mlsanity.com/paper/2601.14004/) (2026)
- [The Dual-Route Model of Induction](https://mlsanity.com/paper/2504.03022/) (2025)
- [Sparse Autoencoder Features for Classifications and Transferability](https://mlsanity.com/paper/2502.11367/) (2025)
- [The Emergence of Abstract Thought in Large Language Models Beyond Any Language](https://mlsanity.com/paper/2506.09890/) (2025)
- [Localized Cultural Knowledge is Conserved and Controllable in Large Language Models](https://mlsanity.com/paper/2504.10191/) (2025)
- [When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners](https://mlsanity.com/paper/2505.15257/) (2025)
- [Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations](https://mlsanity.com/paper/2502.18147/) (2025)
- [Understanding Multilingualism in Mixture-of-Experts LLMs: Routing Mechanism, Expert Specialization, and Layerwise Steering](https://mlsanity.com/paper/2601.14050/) (2026)
- [Tracing Multilingual Representations in LLMs with Cross-Layer Transcoders](https://mlsanity.com/paper/2511.10840/) (2025)
- [Different types of syntactic agreement recruit the same units within large language models](https://mlsanity.com/paper/2512.03676/) (2025)
- [A quantitative analysis of semantic information in deep representations of text and images](https://mlsanity.com/paper/2505.17101/) (2025)
- [How Syntax Specialization Emerges in Language Models](https://mlsanity.com/paper/2505.19548/) (2025)
- [Differential syntactic and semantic encoding in LLMs](https://mlsanity.com/paper/2601.04765/) (2026)
- [Overcoming Vocabulary Constraints with Pixel-level Fallback](https://mlsanity.com/paper/2504.02122/) (2025)
- [Crosscoding Through Time: Tracking Emergence & Consolidation Of Linguistic Representations Throughout LLM Pretraining](https://mlsanity.com/paper/2509.05291/) (2025)
- [Latent Planning Emerges with Scale](https://mlsanity.com/paper/2604.12493/) (2026)
- [Probing LLMs for Multilingual Discourse Generalization Through a Unified Label Set](https://mlsanity.com/paper/2503.10515/) (2025)
- [Rethinking Cross-lingual Gaps from a Statistical Viewpoint](https://mlsanity.com/paper/2510.15551/) (2025)
- [Traveling Across Languages: Benchmarking Cross-Lingual Consistency in Multimodal LLMs](https://mlsanity.com/paper/2505.15075/) (2025)
- [Expand Neurons, Not Parameters](https://mlsanity.com/paper/2510.04500/) (2025)
- [Modality Matching Matters: Calibrating Language Distances for Cross-Lingual Transfer in URIEL+](https://mlsanity.com/paper/2510.19217/) (2025)
- [Multilingual Language Models Encode Script Over Linguistic Structure](https://mlsanity.com/paper/2604.05090/) (2026)
- [Translation in the Wild](https://mlsanity.com/paper/2505.23548/) (2025)
- [Steering Language Models in Multi-Token Generation: A Case Study on Tense and Aspect](https://mlsanity.com/paper/2509.12065/) (2025)
- [Negative Pre-activations Differentiate Syntax](https://mlsanity.com/paper/2509.24198/) (2025)
- [Deep Graph Learning will stall without Network Science](https://mlsanity.com/paper/2502.01177/) (2025)

## Abstract (arXiv)

Human bilinguals often use similar brain regions to process multiple languages, depending on when they learned their second language and their proficiency. In large language models (LLMs), how are multiple languages learned and encoded? In this work, we explore the extent to which LLMs share representations of morphsyntactic concepts such as grammatical number, gender, and tense across languages. We train sparse autoencoders on Llama-3-8B and Aya-23-8B, and demonstrate that abstract grammatical concepts are often encoded in feature directions shared across many languages. We use causal interventions to verify the multilingual nature of these representations; specifically, we show that ablating only multilingual features decreases classifier performance to near-chance across languages. We then use these features to precisely modify model behavior in a machine translation task; this demonstrates both the generality and selectivity of these feature's roles in the network. Our findings suggest that even models trained predominantly on English data can develop robust, cross-lingual abstractions of morphosyntactic concepts.