INDEX

Explanations

animal

np_max-act · gemini-2.0-flash

The neuron activates on tokens referring to animals or non-human species.

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

_users

-0.06

 DispatchQueue

-0.06

독

-0.06

ALS

-0.06

 user

-0.06

 грав

-0.06

)item

-0.06

.mar

-0.06

_dt

-0.06

.add

-0.06

POSITIVE LOGITS

 сот

0.06

 quân

0.06

antt

0.06

_building

0.06

 yatırım

0.06

溶

0.06

 rural

0.06

 unfavorable

0.06

 říj

0.06

煤

0.06

Activations Density 0.030%

animal

The neuron activates on tokens referring to animals or non-human species.

No Comments

No Known Activations