INDEX

Explanations

actions and movements associated with crime and danger

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

assen

-0.16

Ä±s

-0.15

âĹİ

-0.15

æĹ§

-0.15

spaces

-0.14

è·¡

-0.14

aign

-0.14

indow

-0.14

 thÃªm

-0.14

abee

-0.14

POSITIVE LOGITS

 popular

0.20

 busy

0.18

 scene

0.18

 locked

0.17

 disabled

0.17

 populated

0.16

 vehicle

0.16

DF

0.16

 remote

0.15

xc

0.15

Activations Density 0.114%

actions and movements associated with crime and danger

No Comments

No Known Activations