INDEX

Explanations

phrases indicating a return or repetition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ubl

-0.15

restart

-0.14

 Renew

-0.14

 Rehab

-0.14

Wildcard

-0.14

-forward

-0.14

 restart

-0.14

ucid

-0.14

 rehabilit

-0.14

urette

-0.13

POSITIVE LOGITS

 back

0.29

 return

0.28

 terug

0.28

 returned

0.27

è¿ĶåĽŀ

0.26

 returning

0.25

 returns

0.24

return

0.24

 Return

0.23

åĽŀ

0.23

Activations Density 0.099%

phrases indicating a return or repetition

No Comments

No Known Activations