INDEX

Explanations

expressions of gratitude and appreciation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 thank

-0.29

 Thank

-0.27

 thanking

-0.26

 thanked

-0.24

Thank

-0.23

thank

-0.23

 Thanks

-0.22

 thanks

-0.22

 THANK

-0.22

Thanks

-0.19

POSITIVE LOGITS

 appreciated

0.32

 appreciate

0.31

 Apprec

0.28

 appreciation

0.25

 apprec

0.19

ToOne

0.16

uger

0.16

Ã¡p

0.15

olist

0.15

OMUX

0.14

Activations Density 0.063%

expressions of gratitude and appreciation

No Comments

No Known Activations