INDEX

Explanations

structural elements and formatting commands in a document

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

æĥĳ

-0.15

é¡µéĿ¢åŃĺæ¡£å¤ĩä»½

-0.15

esseract

-0.15

iki

-0.14

Ø§Ø¯Ùħ

-0.14

Ø©

-0.14

oxel

-0.14

 Mess

-0.14

 Cust

-0.14

Mess

-0.14

POSITIVE LOGITS

 acknowled

0.23

Conclusion

0.22

Introduction

0.22

 Introduction

0.21

 conclusion

0.21

 introduction

0.19

 Conclusion

0.19

ackle

0.18

 prelim

0.17

 results

0.17

Activations Density 0.024%

structural elements and formatting commands in a document

No Comments

No Known Activations