INDEX

Explanations

references to laundry-related topics and items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

finger

-0.15

lluminate

-0.15

shima

-0.14

/gtest

-0.14

.Redirect

-0.14

 desks

-0.14

sip

-0.13

cÄ±

-0.13

dana

-0.13

sitemap

-0.13

POSITIVE LOGITS

 laundry

0.37

 Laundry

0.33

 washing

0.33

 detergent

0.31

 wash

0.30

 washer

0.29

 laundering

0.28

 Washing

0.28

æ´Ĺ

0.27

 clothes

0.26

Activations Density 0.103%

references to laundry-related topics and items

No Comments

No Known Activations