INDEX

Explanations

mathematical symbols and notation related to functions, particularly in the context of defining properties and behaviors in mathematical theorems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

tero

-0.16

ods

-0.15

Î¯Î³

-0.15

anzi

-0.14

koa

-0.14

udded

-0.14

Ã¡zd

-0.14

ellig

-0.13

ÐµÐ½ÑĮ

-0.13

à¸¸

-0.13

POSITIVE LOGITS

cae

0.15

rieben

0.14

cl

0.14

brig

0.14

PAGE

0.14

OfClass

0.14

="{!!

0.14

steller

0.13

lox

0.13

Pai

0.13

Activations Density 0.067%

mathematical symbols and notation related to functions, particularly in the context of defining properties and behaviors in mathematical theorems

No Comments

No Known Activations