INDEX

Explanations

code files

np_max-act · gemini-2.0-flash

The neuron detects email address patterns (strings containing “@” with username and domain) in code comments or metadata.

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

卫

-0.07

Orth

-0.06

antz

-0.06

usic

-0.06

ographic

-0.06

 democracy

-0.06

衛

-0.06

remember

-0.06

 Django

-0.06

POSITIVE LOGITS

 ایالات

0.08

 bitter

0.07

 tips

0.06

 επι

0.06

».

0.06

_empty

0.06

ptype

0.06

\Config

0.06

,col

0.06

.')↵

0.06

Activations Density 0.012%

code files

The neuron detects email address patterns (strings containing “@” with username and domain) in code comments or metadata.

No Comments

No Known Activations