INDEX

Explanations

terms related to mask mandates and the use of masks for health protection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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¨¿

-0.18

ãĥ³ãĥķ

-0.15

Ø§ÙĪÙĨØ¯

-0.15

HEMA

-0.15

 Sabha

-0.15

apons

-0.15

egade

-0.15

trak

-0.15

ugas

-0.15

iyim

-0.15

POSITIVE LOGITS

AMA

0.15

loys

0.15

åħ·

0.15

ìŀ¡

0.15

Hav

0.15

arine

0.14

 Daniels

0.14

ylon

0.13

 Chew

0.13

elen

0.13

Activations Density 0.012%

terms related to mask mandates and the use of masks for health protection

No Comments

No Known Activations