INDEX

Explanations

Wikipedia extracts

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-version

-0.06

*cos

-0.06

HF

-0.06

 emphasizes

-0.06

 Plates

-0.06

 attractive

-0.06

umbnails

-0.06

relation

-0.06

 depress

-0.06

рукту

-0.06

POSITIVE LOGITS

(iParam

0.07

 Grades

0.07

Am

0.07

 unitOfWork

0.06

-Cola

0.06

Am

0.06

Kom

0.06

_capabilities

0.06

.IContainer

0.06

bit

0.06

Activations Density 0.097%

Wikipedia extracts

No Comments

No Known Activations