INDEX

Explanations

voice

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

ันยายน

-0.07

rend

-0.07

bersome

-0.07

ennial

-0.06

found

-0.06

Bal

-0.06

 suspended

-0.06

 Levy

-0.06

poly

-0.06

POSITIVE LOGITS

 voice

0.09

 Voice

0.09

Voice

0.08

!important

0.08

voice

0.07

::::::::::::::::::::::::::::::::

0.07

 tutoring

0.07

(Op

0.07

 shouts

0.07

 voiture

0.07

Activations Density 0.012%

voice

No Comments

No Known Activations

voice

No Comments

No Known Activations