INDEX

Explanations

references to user interface elements and navigation in software or applications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

.toolbox

-0.16

iquer

-0.16

ora

-0.16

ntag

-0.15

iban

-0.15

Ð¾Ð·Ð°

-0.14

criptor

-0.14

ORA

-0.14

cott

-0.13

idar

-0.13

POSITIVE LOGITS

 dese

0.16

warts

0.14

 Downing

0.14

ogh

0.13

 Active

0.13

ÑİÑģÑĮ

0.13

è®©æĪĳ

0.13

ayÄ±m

0.13

ster

0.13

Activations Density 0.022%

references to user interface elements and navigation in software or applications

No Comments

No Known Activations