INDEX

Explanations

references to user interface component identifiers in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ettel

-0.15

mx

-0.15

vit

-0.14

agate

-0.14

cox

-0.14

bern

-0.14

wer

-0.14

rez

-0.14

dio

-0.14

.names

-0.13

POSITIVE LOGITS

 dikke

0.15

ajor

0.14

imeline

0.14

atÃ³

0.14

 WaitForSeconds

0.14

ActionCreators

0.13

clid

0.13

à¸µà¸¢à¸ĩ

0.13

alaria

0.13

 Overs

0.13

Activations Density 0.002%

references to user interface component identifiers in code

No Comments

No Known Activations