INDEX

Explanations

phrases related to health, medical interventions, and treatment effects

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

omo

-0.15

uze

-0.15

wolf

-0.14

ora

-0.13

boru

-0.13

ì¹ĺ

-0.13

 chim

-0.13

fx

-0.13

_uploaded

-0.12

deo

-0.12

POSITIVE LOGITS

 future

0.37

future

0.29

 Future

0.28

Future

0.27

.future

0.23

.Future

0.23

_future

0.23

UTURE

0.22

 futuro

0.21

 further

0.21

Activations Density 0.155%

phrases related to health, medical interventions, and treatment effects

No Comments

No Known Activations