We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
How well will current interpretability techniques generalize to future models? A relevant case study is Mamba, a recent recurrent architecture with scaling comparable to Transformers. We adapt pre-Mamba techniques to Mamba and partially reverse-engineer the circuit responsible for the Indirect Object Identification (IOI) task. Our techniques provide evidence that 1) Layer 39 is a key bottleneck, 2) Convolutions in layer 39 shift names one position forward, and 3) The name entities are stored linearly in Layer 39's SSM. Finally, we adapt an automatic circuit discovery tool, positional Edge Attribution Patching, to identify a Mamba IOI circuit. Our contributions provide initial evidence that circuit-based mechanistic interpretability tools work well for the Mamba architecture.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2407.14008")
get_code_for_paper("2407.14008")
have("2407.14008")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2407.14008.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2407.14008)
Connect an agent — have() is free.