Archetypal contexts in the neurons of language models: an architecture for intelligence?
cs.CL, cs.AI, cs.LG
Submitted: 2026-11-04
Updated: 2026-11-06
Terminology
Sources
- Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
- Phi-4 Technical Report
- Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs
- Language Modeling Is Compression
- Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers
- Toy Models of Superposition
- Gemma 4 Technical Report
- CLaS-Bench: A Cross-Lingual Alignment and Steering Benchmark
- Finding Neurons in a Haystack: Case Studies with Sparse Probing
- Linearity of Relation Decoding in Transformer Language Models
- On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons
- On Relation-Specific Neurons in Large Language Models
- The Metanym Game: An LLM Benchmark Without Ground Truth That Rises With the Models It Measures
- 2 OLMo 2 Furious
- Analogical Reasoning Inside Large Language Models: Concept Vectors and the Limits of Abstraction
- Cognitive Maps in Large Language Models
- Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models
- Function Vectors in Large Language Models
- Qwen3 Technical Report
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data