INDEX

Explanations

terms related to AI development and research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 Truy

-0.17

Ã¼ny

-0.17

ersed

-0.17

olet

-0.16

ÐºÐ°Ð²

-0.15

oka

-0.15

eÅŁ

-0.15

rophe

-0.14

inyin

-0.14

isco

-0.14

POSITIVE LOGITS

/ic

0.18

ACM

0.18

 rebut

0.15

 tuyá»ĥn

0.15

 Fair

0.15

SIG

0.14

ryo

0.14

 paper

0.14

 crowd

0.14

 fair

0.14

Activations Density 0.085%

terms related to AI development and research

No Comments

No Known Activations