INDEX

Explanations

various forms of punctuation and formatting in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

dit

-0.20

egend

-0.16

ishi

-0.15

ummer

-0.15

xD

-0.14

ãģŁãĤī

-0.14

awn

-0.13

ottes

-0.13

 ÑħÐ¾ÑĤÑı

-0.13

eli

-0.13

POSITIVE LOGITS

Nam

0.20

 thanks

0.18

Jud

0.17

 judging

0.17

 such

0.17

Nam

0.16

Ø§ÙĦØ¥ÙĨØ¬ÙĦÙĬØ²ÙĬØ©

0.16

 Talking

0.16

 handjob

0.16

 Thanks

0.15

Activations Density 0.045%

various forms of punctuation and formatting in the text

No Comments

No Known Activations