INDEX

Explanations

eye

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.27.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

igham

-0.07

_chars

-0.07

////

-0.07

\Common

-0.07

 Limits

-0.06

Output

-0.06

imit

-0.06

WordPress

-0.06

 adhesive

-0.06

////////////////////////////////////////////////////////////////////

-0.06

POSITIVE LOGITS

 Fransız

0.07

 deix

0.06

얘

0.06

izontally

0.06

рії

0.06

숙

0.06

gia

0.06

إ

0.06

niž

0.06

م

0.06

Activations Density 0.003%

eye

No Comments

No Known Activations