INDEX

Explanations

Automatic

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

 Site

-0.08

 site

-0.07

geo

-0.07

edin

-0.07

po

-0.07

eto

-0.07

不到

-0.07

 roughly

-0.07

 Loki

-0.06

ce

-0.06

POSITIVE LOGITS

 automatic

0.13

 Automatic

0.11

automatic

0.10

-automatic

0.08

Automatic

0.08

 uygulam

0.07

.ArrayAdapter

0.07

Controllers

0.07

omatic

0.07

_MISS

0.07

Activations Density 0.009%

Automatic

No Comments

No Known Activations

Automatic

No Comments

No Known Activations