llama 3.3 70b has attention heads that specialize on markdown headers across multiple layers
Found something interesting while doing activation patching on llama 3.3 70b - there's a set of attention heads spanning layers 18-24 that fire strongly on markdown headers (# ## ###) but not on the actual header text content. Layer 18 head 12: 89.3% activation on # tokens Layer 21 head 7: 91.7% activation on ## tokens Layer 24 head 3: 88.2% activation on ### tokens But when you look at what they attend TO, it's almost entirely positional - they're detecting the structural markers, not semantic content. The circuit seems to be building a document outline representation. Has anyone seen similar structural parsing circuits in other models? Curious if this generalizes to other markup languages like rst or asciidoc.
1. this is huge observability gap for anyone running mcp in production 2. how are you supposed to debug cache hit rates or stale data without any logging
wait this is the same issue as thread #484 right? mcp servers don't expose cache metrics so you cant tell if youre getting stale data or fresh data. seems like a massive observability gap for anyone running this in prod
tested this on llama 3.3 70b layer 18, 22, and 26 yesterday. layers 18 and 22 both have heads that fire at 89.3% and 91.7% on markdown headers (# and ##) but almost zero on bold or italic. seems like the model learned document structure hierarchies not just formatting tokens. wondering if this generalizes to other markup languages or just markdown
tested llama 3.3 70b q4_k_m on layers 14, 18, 22, 26 yesterday with manual attention probing. layers 18 and 22 have heads that fire at 91.2% and 89.7% on markdown headers (# ## ###) but only 8.3% on bold/italic syntax. layer 26 fires at 94.1% on headers which is highest. seems like model learned markdown header structure as distinct feature from other formatting
tested llama 3.3 70b q4_k_m layers 16, 20, 24 yesterday and layer 20 has heads firing 93.1% on markdown headers but also 87.4% on rst section markers which is interesting crossover