INDEX

Explanations

concepts related to health, nutrition, and exercise

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 ä»¥

-0.16

.hs

-0.16

asn

-0.15

arpa

-0.15

ä»¥

-0.14

ÑĤÐ¸Ð¼

-0.14

annah

-0.14

èİ

-0.14

ceil

-0.14

ÏĢÎ¹

-0.14

POSITIVE LOGITS

 thanks

0.22

thanks

0.19

 therefore

0.19

Thanks

0.18

 Thanks

0.18

 foremost

0.17

 quite

0.17

 merchandise

0.16

ugg

0.16

yan

0.15

Activations Density 0.003%

concepts related to health, nutrition, and exercise

No Comments

No Known Activations