INDEX

Explanations

prominent individuals and their affiliations in a professional context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Ã´ng

-0.17

Ã¡cil

-0.16

åĽ

-0.16

aits

-0.14

 danmark

-0.13

á»¹

-0.13

oner

-0.13

Opens

-0.13

ansk

-0.13

.opend

-0.13

POSITIVE LOGITS

 earned

0.29

 joined

0.28

 received

0.25

earned

0.24

 grew

0.23

joined

0.23

 rejo

0.22

 works

0.22

 graduated

0.22

 began

0.21

Activations Density 0.103%

prominent individuals and their affiliations in a professional context

No Comments

No Known Activations