INDEX

Explanations

mathematical symbols and notation used in equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

åĩºåĵģ

-0.18

isoft

-0.17

ibri

-0.16

 biÃªn

-0.16

ought

-0.16

geh

-0.16

AGO

-0.16

aps

-0.15

/cms

-0.15

ector

-0.14

POSITIVE LOGITS

equ

0.29

equ

0.26

align

0.24

 equation

0.23

eq

0.21

 align

0.21

 Align

0.19

IEEE

0.19

eq

0.19

-equ

0.19

Activations Density 0.044%

mathematical symbols and notation used in equations

No Comments

No Known Activations