INDEX

Explanations

references to masks and mask-wearing in the context of health and safety

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ç¨¿

-0.17

PasswordEncoder

-0.16

echa

-0.15

ugas

-0.15

agher

-0.15

strike

-0.15

á»§i

-0.15

 ê²Įìĭľë¬¼

-0.14

endor

-0.14

ÛĮÙĨÚ©

-0.14

POSITIVE LOGITS

 Hack

0.17

 worn

0.17

Hack

0.16

Hav

0.14

 familiar

0.14

arine

0.14

 whenever

0.14

pos

0.14

 manufacturers

0.14

ÐµÐ²ÑĭÑħ

0.14

Activations Density 0.017%

references to masks and mask-wearing in the context of health and safety

No Comments

No Known Activations