INDEX

Explanations

and

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

(bot

-0.08

 innate

-0.07

 Presence

-0.06

 Chemistry

-0.06

 alarming

-0.06

—are

-0.06

.Rad

-0.06

AlmostEqual

-0.06

 createStackNavigator

-0.06

 Pharmac

-0.06

POSITIVE LOGITS

USTOM

0.07

 zatím

0.07

oral

0.07

anh

0.07

0.06

campaign

0.06

Owned

0.06

lanmış

0.06

Activations Density 0.000%

and

No Comments

No Known Activations

and

No Comments

No Known Activations