INDEX

Explanations

mathematical variables and functions in a technical document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 cons

-0.15

ellaneous

-0.15

eka

-0.14

egra

-0.14

ysi

-0.14

ÃŃme

-0.14

OrNull

-0.13

ãģĲ

-0.13

eddar

-0.13

etcode

-0.13

POSITIVE LOGITS

.tk

0.15

jang

0.14

à¸¢à¸ĩ

0.14

uta

0.14

htag

0.14

usp

0.14

 nevid

0.14

rieb

0.14

ths

0.13

Activations Density 0.187%

mathematical variables and functions in a technical document

No Comments

No Known Activations