INDEX

Explanations

instances of the word "Appendix" and related structures in the context of documents or references

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

Specifier

-0.17

rep

-0.16

skins

-0.15

åĨµ

-0.15

mony

-0.14

GROUND

-0.14

ãĥ³ãĥĳ

-0.14

rap

-0.14

emaker

-0.14

oro

-0.14

POSITIVE LOGITS

ices

0.28

ix

0.27

 append

0.25

append

0.22

ures

0.22

icit

0.21

 Append

0.20

endum

0.20

IX

0.20

iks

0.19

Activations Density 0.025%

instances of the word "Appendix" and related structures in the context of documents or references

No Comments

No Known Activations