INDEX

Explanations

Code imports/statements

np_max-act · gemini-2.0-flash

This neuron activates on Python import statements (the “import” and “from … import” lines).

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

 racer

-0.07

 Prod

-0.07

nick

-0.06

 membership

-0.06

';';

-0.06

_metadata

-0.06

 contempl

-0.06

prop

-0.06

/team

-0.06

:M

-0.06

POSITIVE LOGITS

cılar

0.07

 bát

0.06

 complains

0.06

PageSize

0.06

wij

0.06

.El

0.06

션

0.06

.CodeAnalysis

0.06

 Publishers

0.06

 Bylo

0.06

Activations Density 0.015%

Code imports/statements

This neuron activates on Python import statements (the “import” and “from … import” lines).

No Comments

No Known Activations