INDEX

Explanations

distinctions and differences between various concepts and terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 cÃ©lib

-0.16

;element

-0.16

Æł

-0.15

Ð½Ð¾Ð·

-0.14

.UnitTesting

-0.14

orgia

-0.14

Â·Â·

-0.14

ÑĢÐ¾Ñī

-0.14

lef

-0.14

Ð¾Ð³Ð¾Ð´

-0.14

POSITIVE LOGITS

 mere

0.24

 merely

0.20

mere

0.17

 trav

0.16

 just

0.16

arta

0.14

 being

0.14

end

0.14

 simply

0.14

 åĤ

0.14

Activations Density 0.132%

distinctions and differences between various concepts and terms

No Comments

No Known Activations