INDEX

Explanations

is

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

 conte

-0.06

_clr

-0.06

(*(

-0.06

 forCellReuseIdentifier

-0.06

یزی

-0.06

 tents

-0.06

 şaş

-0.06

BOOK

-0.06

없음

-0.06

	engine

-0.06

POSITIVE LOGITS

 Seks

0.06

.OrdinalIgnoreCase

0.06

.receiver

0.06

cro

0.06

 spat

0.06

 lessen

0.06

 BusinessException

0.06

.der

0.06

 Disease

0.06

igaret

0.06

Activations Density 0.094%

is

No Comments

No Known Activations