INDEX

Explanations

references to awards and recognitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ults

-0.18

avers

-0.16

avr

-0.16

//---------------------------------------------------------------------------↵↵

-0.15

opp

-0.15

pone

-0.15

acher

-0.15

-builder

-0.14

Î´Î¹Î¿

-0.14

eldorf

-0.14

POSITIVE LOGITS

 winning

0.44

-winning

0.39

win

0.32

 Winning

0.31

win

0.23

Win

0.23

 nominated

0.21

WIN

0.20

-w

0.20

 losing

0.19

Activations Density 0.009%

references to awards and recognitions

No Comments

No Known Activations