# Demystifying the Slash Pattern in Attention: The Role of RoPE

arXiv: https://arxiv.org/abs/2601.08297 · HTML: https://mlsanity.com/paper/2601.08297/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jan 2026.

## Built on by (most cited first, 4 of 4)

- [AdaRoPE: Not All Attention Heads Should Rotate and Scale Equally](https://mlsanity.com/paper/2607.19363/) (2026)
- [Mitigating Many-shot Jailbreak Attacks with One Single Demonstration](https://mlsanity.com/paper/2605.08277/) (2026)
- [WavePrune: One period is often enough for RoPE](https://mlsanity.com/paper/2610.06963/) (2026)
- [SPIN: Shadow Predictive Indexer for Sparse Attention](https://mlsanity.com/paper/2610.09025/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) often exhibit slash attention patterns, where attention scores concentrate along the Delta-th sub-diagonal for some offset Delta. These patterns play a key role in passing information across tokens. But why do they emerge? In this paper, we demystify the emergence of these Slash-Dominant Heads (SDHs) from both empirical and theoretical perspectives. First, by analyzing open-source LLMs, we find that SDHs are intrinsic to models and generalize to out-of-distribution prompts. To explain the intrinsic emergence, we analyze the queries, keys, and Rotary Position Embedding (RoPE), which jointly determine attention scores. Our empirical analysis reveals two characteristic conditions of SDHs: (1) Queries and keys are almost rank-one, and (2) RoPE is dominated by medium- and high-frequency components. Under these conditions, queries and keys are nearly identical across tokens, and interactions between medium- and high-frequency components of RoPE give rise to SDHs. Beyond empirical evidence, we theoretically show that these conditions are sufficient to ensure the emergence of SDHs by formalizing them as our modeling assumptions. Particularly, we analyze the training dynamics of a shallow Transformer equipped with RoPE under these conditions, and prove that models trained via gradient descent exhibit SDHs. The SDHs generalize to out-of-distribution prompts.