INDEX

Explanations

program

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

 detects

-0.06

ittal

-0.06

ISK

-0.06

 stellt

-0.06

SSE

-0.06

aje

-0.06

 diss

-0.06

Lt

-0.06

itele

-0.06

riors

-0.06

POSITIVE LOGITS

 program

0.18

 Program

0.18

 programs

0.18

 Programs

0.15

 programme

0.14

Program

0.13

 Programme

0.12

 programmes

0.12

program

0.11

 PROGRAM

0.10

Activations Density 0.039%

program

No Comments

No Known Activations