INDEX

Explanations

:

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 setPassword

-0.07

 penetr

-0.07

OP

-0.07

 boundary

-0.07

크

-0.07

 classifications

-0.07

Vector

-0.06

 China

-0.06

texto

-0.06

 Cancer

-0.06

POSITIVE LOGITS

گاه

0.06

.repositories

0.06

 пов

0.06

************************************************************************

0.06

_cre

0.06

ICLE

0.06

/%

0.06

avorites

0.06

%%%

0.06

Activations Density 0.051%

:

No Comments

No Known Activations