INDEX

Explanations

complex mathematical expressions and discussions about mathematical concepts

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

olle

-0.17

oola

-0.17

ÑĢÑĥÐ´

-0.15

à¤¦à¤°

-0.15

jest

-0.15

ister

-0.15

Ð½ÑĸÑģÑĤ

-0.14

 Benef

-0.14

Tel

-0.13

pers

-0.13

POSITIVE LOGITS

 Kurum

0.16

istrovstvÃŃ

0.16

rlen

0.15

ypy

0.15

abox

0.15

Tie

0.14

Ð°Ð½Ð¸ÑĨ

0.14

Î»Î¼

0.14

uncios

0.14

Hp

0.13

Activations Density 0.053%

complex mathematical expressions and discussions about mathematical concepts

No Comments

No Known Activations