INDEX

Explanations

mentions of journalistic or media-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 borr

-0.17

å¸ĸ

-0.15

ppo

-0.15

ÐµÑģÑı

-0.14

ãĥ¼ãĥĢ

-0.14

acons

-0.13

aat

-0.13

Ð»Ð°Ð±

-0.13

 Fund

-0.13

POSITIVE LOGITS

 press

0.39

PR

0.38

PR

0.34

 Press

0.31

press

0.31

Press

0.28

 media

0.28

 PRESS

0.27

 journalists

0.26

 MEDIA

0.25

Activations Density 0.137%

mentions of journalistic or media-related terms

No Comments

No Known Activations