INDEX

Explanations

documentaries, TV shows

np_max-act · gemini-2.0-flash

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

<td

-0.06

 repent

-0.06

دة

-0.06

 týden

-0.06

 Rupert

-0.06

 здат

-0.06

Když

-0.06

 Feed

-0.06

設定

-0.06

 hour

-0.06

POSITIVE LOGITS

ByKey

0.06

	container

0.06

Generally

0.06

OLER

0.06

 MyBase

0.06

 critically

0.06

_Msk

0.06

.softmax

0.06

 Generally

0.06

Activations Density 0.023%

documentaries, TV shows

No Comments

No Known Activations

documentaries, TV shows

No Comments

No Known Activations