INDEX

Explanations

phrases related to health and safety warnings or guidelines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ordinate

-0.15

iyon

-0.14

 rather

-0.14

 Friendly

-0.13

Ge

-0.13

ilet

-0.13

æģµ

-0.13

/downloads

-0.13

statt

-0.13

Ã¦r

-0.13

POSITIVE LOGITS

ÑħÐ¾Ð´Ð¸Ð¼

0.15

imd

0.14

 vidÃ©

0.14

lesc

0.14

 Bilim

0.14

rollo

0.14

feof

0.13

 Rodrig

0.13

elidir

0.13

iever

0.13

Activations Density 0.404%

phrases related to health and safety warnings or guidelines

No Comments

No Known Activations