Lagged Coupling: Internal Representations Become Readable Before They Become Causal

arXiv:2609.01048 · cs.CL, cs.AI · Submitted 2026-09-01 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-09-01

Updated: 2026-09-01

Terminology

• Steering — 18× in this paper · explained in 2 episodes
• AUROC — 9× in this paper · explained in 2 episodes
• Transformer — 5× in this paper · explained in 2 episodes
• Aggregation — 4× in this paper · explained in 1 episode
• Generalization — 4× in this paper · explained in 13 episodes
• Interpretability — 4× in this paper · explained in 15 episodes
• Accuracy — 3× in this paper · explained in 1 episode
• Abstraction — 2× in this paper · explained in 1 episode
• Activation Steering — 2× in this paper · explained in 4 episodes
• In-Context Learning — 2× in this paper · explained in 4 episodes
• Linear probe — 2× in this paper · explained in 2 episodes
• Mechanistic interpretability — 2× in this paper · explained in 2 episodes
• Representation Engineering — 2× in this paper · explained in 2 episodes
• Scaling Laws — 2× in this paper · explained in 4 episodes
• Ab Initio — 1× in this paper · explained in 1 episode
• Activation Patching — 1× in this paper · explained in 2 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Robustness — 1× in this paper · explained in 5 episodes

Sources

• 2 OLMo 2 Furious
• Scaling Laws for Neural Language Models
• Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
• Causal Abstractions of Neural Networks
• Steering Language Models With Activation Engineering
• Representation Engineering: A Top-Down Approach to AI Transparency
• Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
• Towards Best Practices of Activation Patching in Language Models: Metrics and Methods

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering