Which the Eye Fears: Writing with Read-Blindness Explains Massive Activations in Transformers

arXiv:2609.35630 · cs.CL, cs.LG · Submitted 2026-09-28 · Read on arXiv

cs.CL, cs.LG

Submitted: 2026-09-28

Updated: 2026-09-28

Code: https://github.com/huggingface/transformers

Terminology

• Transformer — 24× in this paper · explained in 2 episodes
• Alignment — 5× in this paper · explained in 1 episode
• Trace — 3× in this paper · explained in 2 episodes
• Transformer Architecture — 3× in this paper · explained in 2 episodes
• AdamW Optimizer — 2× in this paper · explained in 1 episode
• KV cache — 2× in this paper · explained in 3 episodes
• Perplexity — 2× in this paper · explained in 3 episodes
• Quantization — 2× in this paper · explained in 12 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Inverse Participation Ratio (IPR) — 1× in this paper · explained in 2 episodes
• Mechanistic interpretability — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes

Sources

• Hidden Dynamics of Massive Activations in Transformer Training
• A Refined Analysis of Massive Activations in LLMs
• Massive Activations in Large Language Models
• The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks
• Qwen3 Technical Report
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• The Super Weight in Large Language Models

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