INDEX

Explanations

references to laundry-related tasks and products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 Brace

-0.16

åĪĢ

-0.16

 desks

-0.15

Cz

-0.15

ICES

-0.14

istrovstvÃŃ

-0.14

itchen

-0.14

ihn

-0.14

finger

-0.14

decorate

-0.14

POSITIVE LOGITS

 laundry

0.33

 detergent

0.32

 Laundry

0.30

 washing

0.28

 clothes

0.27

 washer

0.27

 deter

0.27

 dryer

0.26

 tumble

0.26

 Washing

0.25

Activations Density 0.064%

references to laundry-related tasks and products

No Comments

No Known Activations