INDEX

Explanations

mathematical concepts and notations

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

 circ

-0.14

 spotted

-0.14

Ð¼Ð¾Ð²

-0.14

wand

-0.13

Ð½Ð¾Ð¶

-0.13

Ã¡p

-0.13

hd

-0.13

adele

-0.13

Uri

-0.13

Lat

-0.13

POSITIVE LOGITS

è´

0.19

enie

0.17

è³¢

0.15

wich

0.15

Ð¾Ð¼ÐµÑĢ

0.14

erna

0.14

erville

0.14

oins

0.14

Ð´ÑĢÐ¾Ð¼

0.14

Activations Density 0.129%

mathematical concepts and notations

No Comments

No Known Activations