INDEX

Explanations

mathematical terms and structures, particularly those related to measures, dimensions, and sets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

fra

-0.16

ada

-0.15

adera

-0.15

thur

-0.14

Ã³ln

-0.14

ÐµÐ½ÑĮ

-0.14

åħ¶ä¸Ń

-0.13

uld

-0.13

chem

-0.13

udson

-0.13

POSITIVE LOGITS

µľ

0.16

killer

0.15

 Aires

0.14

_attempts

0.13

-League

0.13

.GPIO

0.13

Retry

0.13

-league

0.13

NotFoundException

0.13

atoes

0.13

Activations Density 0.103%

mathematical terms and structures, particularly those related to measures, dimensions, and sets

No Comments

No Known Activations