AI Cog Map

AI Model Cognitive Mapping Tool

connecting...

Idle

waiting for inference

Cognitive Depth Attention & MLP

Layer Activation Map

Activation Change (delta)

Component Reference

Component	What it does	High activation means
layer_output	Full layer contribution to residual stream	Overall layer importance
attention	Attention block aggregated output	Token-to-token relationships active
attention_conv	Mamba-style convolution in hybrid attention	Local sequential pattern matching
attention_qkv	Query/Key/Value projections	Complex attention query formation
attention_gate	Attention gating mechanism	Selective attention filtering
attention_proj	Attention output projections	Compressed attention output
mlp	Feed-forward network block	Knowledge recall and reasoning
mlp_gate_up	MLP gated projection (SwiGLU)	Which knowledge neurons fired
mlp_down	MLP output down-projection	Compressed reasoning output
layernorm_input	Pre-attention normalization	Signal scale into attention
layernorm_post	Post-attention normalization	Signal scale into MLP

Cognitive States

State	Pattern	Typical tasks
Attending	Attention energy > 65% of total	Reading context, following references
Reasoning	MLP dominant, deep layers active	Math, logic, code generation
Structuring	MLP dominant, early layers active	Parsing syntax, organizing output
Recalling	MLP gate projections highest	Factual recall, knowledge lookup
Searching	Low variance across layers	Uncertain, exploring possibilities
Generating	Deep layers > 50% of total energy	Token generation, text completion
Processing	No dominant pattern	Mixed or transitional processing