INDEX

Explanations

subset

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

Inicial

-0.08

 calm

-0.07

 INTERNATIONAL

-0.07

 operations

-0.07

MISSION

-0.07

์ค

-0.07

 Operations

-0.07

.command

-0.07

Time

-0.07

chantment

-0.07

POSITIVE LOGITS

 subset

0.16

 subsets

0.14

 Subset

0.10

subset

0.10

Subset

0.08

_subset

0.07

 minority

0.07

uet

0.07

Het

0.07

OTS

0.07

Activations Density 0.004%

subset

No Comments

No Known Activations