INDEX

Explanations

descriptive terms for clothing and fashion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

-0.15

rippling

-0.14

çıł

-0.14

ixe

-0.14

 toes

-0.13

èĦĤ

-0.13

endas

-0.13

rine

-0.13

alim

-0.13

oken

-0.13

POSITIVE LOGITS

pul

0.33

 jumper

0.30

 shirt

0.29

 vest

0.29

 jacket

0.27

 jumps

0.27

 sweater

0.27

 dress

0.25

 crop

0.25

 cardi

0.24

Activations Density 0.178%

descriptive terms for clothing and fashion

No Comments

No Known Activations