INDEX

Explanations

references to geographical regions, specifically in North and South America

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

URLException

-0.14

icode

-0.14

ycz

-0.14

aed

-0.14

UsageId

-0.14

 Slov

-0.14

.si

-0.14

lander

-0.14

uard

-0.14

uin

-0.14

POSITIVE LOGITS

 America

0.25

 Europe

0.23

 Asia

0.22

Hem

0.19

America

0.19

 america

0.18

 Africa

0.17

Europe

0.17

Asia

0.16

/S

0.15

Activations Density 0.019%

references to geographical regions, specifically in North and South America

No Comments

No Known Activations