INDEX

Explanations

lor

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 McCarthy

-0.07

angan

-0.07

 Abyss

-0.07

洋

-0.07

deniz

-0.06

.acquire

-0.06

 Ivan

-0.06

 insights

-0.06

PropertyDescriptor

-0.06

POSITIVE LOGITS

 convened

0.07

 ascertain

0.06

 lúc

0.06

 coupling

0.06

IF

0.06

caffold

0.06

_Mode

0.06

 corrosion

0.06

(Post

0.06

_uuid

0.06

Activations Density 0.006%

lor

No Comments

No Known Activations