INDEX

Explanations

references to specific brands and their products in relation to footwear

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 sleeve

-0.21

 sleeves

-0.20

 arms

-0.17

 Neck

-0.17

 Sleeve

-0.17

 beard

-0.16

 Arms

-0.16

 Towers

-0.16

 neck

-0.15

neck

-0.15

POSITIVE LOGITS

 shoes

0.39

 footwear

0.38

 shoe

0.37

éŀĭ

0.36

 Shoes

0.35

 Shoe

0.32

 heel

0.32

toe

0.31

 sandals

0.31

Toe

0.30

Activations Density 0.120%

references to specific brands and their products in relation to footwear

No Comments

No Known Activations