INDEX

Explanations

phrases indicating risk and trust in technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

AndGet

-0.15

arÃ¡

-0.15

erville

-0.14

ilis

-0.14

 Ð¸ÑģÑħÐ¾Ð´

-0.14

uania

-0.14

rak

-0.14

euillez

-0.14

sik

-0.14

atische

-0.14

POSITIVE LOGITS

 thereof

0.28

its

0.20

 therein

0.19

 associated

0.17

it

0.17

ãģĿãģĵ

0.15

associated

0.15

iffe

0.14

å®ĥ

0.14

Rh

0.14

Activations Density 0.186%

phrases indicating risk and trust in technology

No Comments

No Known Activations