INDEX

Explanations

references to individuals and their roles or contributions in various contexts

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

upe

-0.15

opath

-0.15

debit

-0.15

vale

-0.14

jian

-0.14

Ã¡p

-0.14

Ã¶m

-0.14

 lÃ¡i

-0.13

 Fleming

-0.13

afi

-0.13

POSITIVE LOGITS

 ÙĪÙĦØ¯

0.16

èĨ

0.15

-corner

0.15

è±Ĩ

0.15

eyin

0.14

ikat

0.14

 Excell

0.14

 Colon

0.14

orent

0.13

ulton

0.13

Activations Density 0.058%

references to individuals and their roles or contributions in various contexts

No Comments

No Known Activations