INDEX

Explanations

references to cultural practices and traditions, particularly those involving dress codes

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

CORD

-0.17

amage

-0.14

Jer

-0.14

auen

-0.14

à¸²à¸¢à¸Ļ

-0.14

adius

-0.13

cord

-0.13

 Traverse

-0.13

ÛĮØ±Ùĩ

-0.13

POSITIVE LOGITS

hij

0.46

Hij

0.41

 veil

0.36

bur

0.34

ve

0.32

ni

0.29

Ve

0.28

 covering

0.28

 modest

0.28

covering

0.27

Activations Density 0.049%

references to cultural practices and traditions, particularly those involving dress codes

No Comments

No Known Activations