INDEX

Explanations

Comments

np_max-act · gemini-2.0-flash

The neuron responds to bits of page chrome that show comment or reaction metadata (e.g. “Comments,” vote counts, “Share,” etc.).

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

 thế

-0.07

िन

-0.07

أ

-0.06

 fore

-0.06

_FUNC

-0.06

makt

-0.06

 Terrorism

-0.06

Containers

-0.06

_books

-0.06

.Roles

-0.06

POSITIVE LOGITS

 апреля

0.07

emble

0.07

ofi

0.06

_UDP

0.06

.om

0.06

 backyard

0.06

Anonymous

0.06

 Hollande

0.06

igated

0.06

 devez

0.06

Activations Density 0.005%

Comments

The neuron responds to bits of page chrome that show comment or reaction metadata (e.g. “Comments,” vote counts, “Share,” etc.).

No Comments

No Known Activations