INDEX

Explanations

punctuation marks and specific formatting characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

actionDate

-0.17

outh

-0.16

ictionary

-0.15

matchCondition

-0.15

throat

-0.15

itical

-0.15

styleType

-0.15

aimassage

-0.15

uniacid

-0.14

uary

-0.14

POSITIVE LOGITS

estre

0.22

est

0.21

autÃ©

0.20

esto

0.20

lÃŃ

0.19

estruct

0.19

como

0.19

tÃŃ

0.19

su

0.18

todos

0.18

Activations Density 0.037%

punctuation marks and specific formatting characters

No Comments

No Known Activations