INDEX

Explanations

references to laundry and cleaning items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

åĪĢ

-0.16

ãĥ³ãĥģ

-0.15

ÑĸÑĩ

-0.15

OTS

-0.15

.Serve

-0.15

 solder

-0.15

sonian

-0.14

ê³¤

-0.14

Ø¬Ø§Øª

-0.14

Cz

-0.14

POSITIVE LOGITS

 tumble

0.32

 detergent

0.30

 laundry

0.29

 deter

0.28

 washing

0.27

 washer

0.26

 Laundry

0.26

tum

0.26

 clothes

0.26

 dryer

0.25

Activations Density 0.066%

references to laundry and cleaning items

No Comments

No Known Activations