INDEX

Explanations

references to time periods and significant changes over the years

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

uya

-0.15

Î¼Î¹

-0.15

 comple

-0.14

 suscept

-0.14

ãģĮåĩº

-0.14

-prepend

-0.13

ëĭ¨

-0.13

idy

-0.13

è¾¾åĪ°

-0.13

eso

-0.13

POSITIVE LOGITS

saw

0.45

 sees

0.43

 witness

0.32

 witnessed

0.31

see

0.31

 witnessing

0.30

 seeing

0.28

 brings

0.28

 bring

0.28

Saw

0.28

Activations Density 0.150%

references to time periods and significant changes over the years

No Comments

No Known Activations