INDEX

Explanations

Foreign language, code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.23.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 strongest

-0.07

 raster

-0.07

 pitcher

-0.06

 дает

-0.06

Seven

-0.06

ũi

-0.06

losed

-0.06

Camera

-0.06

 Суд

-0.06

럼

-0.06

POSITIVE LOGITS

ardım

0.06

_cn

0.06

 Herbert

0.06

 deutschland

0.06

-Bold

0.06

_MATERIAL

0.06

ValueHandling

0.06

ÜM

0.06

 المللی

0.06

production

0.06

Activations Density 0.001%

Foreign language, code

No Comments

No Known Activations