INDEX

Explanations

references to popular culture and media

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

amble

-0.16

 *----------------------------------------------------------------

-0.15

kop

-0.15

usal

-0.14

heck

-0.14

quer

-0.14

allen

-0.13

à¤¾à¤°à¤£

-0.13

byt

-0.13

nesty

-0.13

POSITIVE LOGITS

uzey

0.14

 doby

0.14

Ð»Ð°Ð²Ð°

0.13

 Ð´ÐµÑĢ

0.13

 Dell

0.13

 hete

0.13

.chunk

0.13

 desar

0.13

enaire

0.13

 Hend

0.13

Activations Density 0.100%

references to popular culture and media

No Comments

No Known Activations