INDEX

Explanations

terms related to disinfection and sanitation practices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 resc

-0.16

 mend

-0.15

 rescue

-0.15

Ð¾ÑĢÐ¾Ð²

-0.15

olie

-0.14

FD

-0.14

/gif

-0.14

FD

-0.14

extr

-0.14

 wind

-0.13

POSITIVE LOGITS

 disin

0.27

 killing

0.27

 kills

0.25

kills

0.24

 Kills

0.24

 kill

0.24

à¸Ĩ

0.23

 diá»ĩt

0.22

 steril

0.22

 germ

0.21

Activations Density 0.129%

terms related to disinfection and sanitation practices

No Comments

No Known Activations