INDEX

Explanations

references to historical events and their timelines

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

erdale

-0.16

 Ð±Ð¾ÑĢÐ¾ÑĤÑĮ

-0.16

polator

-0.15

ngoing

-0.15

DonaldTrump

-0.14

 ÑĩÐ¸ÑģÐ»Ðµ

-0.14

ä¹ħ

-0.14

 future

-0.14

ıi

-0.14

viewer

-0.13

POSITIVE LOGITS

 arrival

0.34

 publication

0.33

 completion

0.31

 advent

0.29

 expiration

0.29

 release

0.28

 start

0.27

 launch

0.27

 introduction

0.27

 conclusion

0.26

Activations Density 0.295%

references to historical events and their timelines

No Comments

No Known Activations