INDEX

Explanations

mathematical symbols and numeric expressions related to formulas and calculations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

èĵ

-0.19

avel

-0.16

esub

-0.16

Slf

-0.15

AFE

-0.15

ungan

-0.15

osu

-0.14

aginator

-0.14

liner

-0.14

APPER

-0.14

POSITIVE LOGITS

ASHBOARD

0.15

oon

0.15

Î¹

0.14

rand

0.14

ulty

0.14

Shape

0.13

 sensit

0.13

illac

0.13

eated

0.13

 à¤¸à¤µ

0.13

Activations Density 0.031%

mathematical symbols and numeric expressions related to formulas and calculations

No Comments

No Known Activations