# The Token Before the Value Is the Key: How Hybrid Architectures Organize Induction Circuits

arXiv: https://arxiv.org/abs/2609.15545 · HTML: https://mlsanity.com/paper/2609.15545/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 30 references that are in the map.
- First posted on arXiv 14 Sep 2026.

## Builds on (most cited first, 28 of 28)

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Gated Delta Networks: Improving Mamba2 with Delta Rule](https://mlsanity.com/paper/2412.06464/) (2024)
- [Gated Linear Attention Transformers with Hardware-Efficient Training](https://mlsanity.com/paper/2312.06635/) (2023)
- [Jamba: A Hybrid Transformer-Mamba Language Model](https://mlsanity.com/paper/2403.19887/) (2024)
- [Towards Best Practices of Activation Patching in Language Models: Metrics and Methods](https://mlsanity.com/paper/2309.16042/) (2023)
- [Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models](https://mlsanity.com/paper/2402.19427/) (2024)
- [Repeat After Me: Transformers are Better than State Space Models at Copying](https://mlsanity.com/paper/2402.01032/) (2024)
- [Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability](https://mlsanity.com/paper/2301.04709/) (2023)
- [Zoology: Measuring and Improving Recall in Efficient Language Models](https://mlsanity.com/paper/2312.04927/) (2023)
- [Kimi Linear: An Expressive, Efficient Attention Architecture](https://mlsanity.com/paper/2510.26692/) (2025)
- [Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling](https://mlsanity.com/paper/2406.07522/) (2024)
- [Kimi K3: Open Frontier Intelligence](https://mlsanity.com/paper/2607.24653/) (2026)
- [Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks](https://mlsanity.com/paper/2402.04248/) (2024)
- [In-Context Language Learning: Architectures and Algorithms](https://mlsanity.com/paper/2401.12973/) (2024)
- [What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation](https://mlsanity.com/paper/2404.07129/) (2024)
- [A Systematic Analysis of Hybrid Linear Attention](https://mlsanity.com/paper/2507.06457/) (2025)
- [On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability](https://mlsanity.com/paper/2608.30320/) (2026)
- [Olmo Hybrid: From Theory to Practice and Back](https://mlsanity.com/paper/2604.03444/) (2026)
- [Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism](https://mlsanity.com/paper/2504.18574/) (2025)
- [Short window attention enables long-term memorization](https://mlsanity.com/paper/2509.24552/) (2025)
- [Mechanistic evaluation of Transformers and state space models](https://mlsanity.com/paper/2505.15105/) (2025)
- [Predicting the Emergence of Induction Heads in Language Model Pretraining](https://mlsanity.com/paper/2511.16893/) (2025)
- [On the Emergence of Induction Heads for In-Context Learning](https://mlsanity.com/paper/2511.01033/) (2025)
- [Rethinking the Role of Efficient Attention in Hybrid Architectures](https://mlsanity.com/paper/2606.15378/) (2026)
- [Expressivity-Efficiency Tradeoffs for Hybrid Sequence Models](https://mlsanity.com/paper/2603.08859/) (2026)
- [Modern Transformers Are Implicit Hybrids: From Functional Differentiation to Principled Hybrid Architecture Design](https://mlsanity.com/paper/2609.02986/) (2026)
- [Invariant Learning Dynamics of Transformers in Inductive Reasoning Tasks](https://mlsanity.com/paper/2607.11875/) (2026)

## Abstract (arXiv)

Hybrid language models can improve capability as well as efficiency, raising the question of how architectural complementarity becomes learned computation. We examine the established induction roles of Carrying predecessor information, Matching a source by content, and Copying its value. How are these position-sensitive and content-based computations allocated across heterogeneous layers? We introduce layer-type-agnostic paired probes that track Carrying and Matching through a common block-update interface. In recurrent--global and local--global hybrids, Carrying concentrates in efficient layers and Matching in global receivers. The measured local contribution concentrates on lag one: the token immediately before the historical value. Changing predecessor support through lag-one masking, convolution removal, or early learning-rate reduction can relocate Carrying and Matching between stages. Source-key restoration and fixed-value selection trace the receiver's dependence on the prepared source. These interventions also change natural-text recall, with outcomes depending on configuration and target. Varying local windows and induction-enriched training text changes the early development of functional Carrying and Matching, connecting architectural priors and training evidence to formation timing. Together, the probes and interventions shift the explanatory focus upstream: the organization of Matching follows how Carrying is learned. The token before the value provides a concrete link between a hybrid's architecture, circuit development, and recall. Code is available in https://github.com/ckpassenger/bind-match-copy/tree/main.