INDEX

Explanations

sections of text related to background information and historical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ibile

-0.15

 previews

-0.15

urf

-0.14

elp

-0.14

 jinak

-0.13

amak

-0.13

aman

-0.13

att

-0.13

POSITIVE LOGITS

Edit

0.45

 Edit

0.45

 edit

0.42

edit

0.42

 ç¼ĸè¾ĳ

0.35

_edit

0.31

-edit

0.31

.Edit

0.29

.edit

0.28

 íİ¸ì§ĳ

0.28

Activations Density 0.042%

sections of text related to background information and historical context

No Comments

No Known Activations