INDEX

Explanations

creators and contributors associated with various projects and artistic works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

Ð°Ð½ÑģÐ¸

-0.15

anos

-0.15

zel

-0.14

alte

-0.14

å®¶çļĦ

-0.14

.cf

-0.14

enders

-0.13

others

-0.13

ologne

-0.13

Ø±ÙĤ

-0.13

POSITIVE LOGITS

 ourselves

0.21

 myself

0.20

our

0.20

Mr

0.19

moi

0.17

/by

0.16

 author

0.16

 master

0.16

bler

0.16

Activations Density 0.212%

creators and contributors associated with various projects and artistic works

No Comments

No Known Activations