INDEX

Explanations

able

np_max-act · gemini-2.0-flash

This neuron detects the special header‐delimiter tokens (e.g. `<|start_header_id|>` and `<|end_header_id|>`) that mark the conversation metadata sections.

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 нового

-0.07

 discoveries

-0.07

 tastes

-0.06

 Authors

-0.06

 Herc

-0.06

_sample

-0.06

 Beef

-0.06

.Guna

-0.06

riors

-0.06

_constant

-0.06

POSITIVE LOGITS

'")↵

0.07

lex

0.06

 배열

0.06

(){}↵

0.06

ு

0.06

 exped

0.06

 初始化

0.06

cs

0.06

 ceasefire

0.06

登

0.06

Activations Density 0.049%

able

This neuron detects the special header‐delimiter tokens (e.g. `<|start_header_id|>` and `<|end_header_id|>`) that mark the conversation metadata sections.

No Comments

No Known Activations