INDEX

Explanations

comma

np_max-act · gemini-2.0-flash

The neuron activates on words related to sociopolitical advocacy and collective action (e.g., art, legislation, action, allies, power).

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

ArgsConstructor

-0.07

องค

-0.07

dip

-0.07

-gay

-0.07

heard

-0.07

 memories

-0.07

APT

-0.06

.Article

-0.06

うち

-0.06

POSITIVE LOGITS

ς

0.07

 tục

0.07

 noreferrer

0.07

 DataType

0.07

žený

0.06

 pregn

0.06

 verbess

0.06

 issuer

0.06

\Client

0.06

 Wedding

0.06

Activations Density 0.172%

comma

The neuron activates on words related to sociopolitical advocacy and collective action (e.g., art, legislation, action, allies, power).

No Comments

No Known Activations