INDEX

Explanations

references to political leaders and their actions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å®¾

-0.17

benh

-0.17

 Osman

-0.17

ello

-0.16

 Lans

-0.16

åĿª

-0.15

/epl

-0.15

 ê¸°ìŀĲ

-0.14

anga

-0.14

 oslo

-0.14

POSITIVE LOGITS

Ay

0.28

 Exped

0.28

ay

0.28

 Revolutionary

0.24

Ay

0.23

 cler

0.23

 Guards

0.22

 Supreme

0.22

 Guard

0.22

 Guardians

0.22

Activations Density 0.044%

references to political leaders and their actions

No Comments

No Known Activations