INDEX

Explanations

questions or phrases expressing curiosity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ollapsed

-0.15

æī¾åĪ°

-0.14

hopefully

-0.14

oter

-0.13

avr

-0.13

 ëĲ©ëĭĪëĭ¤

-0.13

enÃŃ

-0.13

eso

-0.13

à¤¾à¤¹à¤¤

-0.12

agog

-0.12

POSITIVE LOGITS

 wouldn

0.31

 hasn

0.31

 shouldn

0.31

 would

0.30

 should

0.30

 aren

0.28

 couldn

0.28

ever

0.28

 didn

0.27

isn

0.26

Activations Density 0.030%

questions or phrases expressing curiosity

No Comments

No Known Activations