INDEX

Explanations

academic references and citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

lingen

-0.16

 Magazine

-0.16

uchar

-0.15

eva

-0.15

leftright

-0.15

Clip

-0.15

 Linh

-0.14

Sul

-0.14

opian

-0.14

Graphics

-0.14

POSITIVE LOGITS

 chapters

0.23

0.20

 Springer

0.20

 Chapters

0.20

å·»

0.19

 Chapter

0.19

 chapter

0.18

Ã¤ch

0.18

Chapter

0.18

lei

0.17

Activations Density 0.059%

academic references and citations

No Comments

No Known Activations