INDEX

Explanations

academic qualifications and degrees

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ebi

-0.16

oz

-0.16

ogh

-0.15

ÑĢÐµÑģÑĤ

-0.14

itez

-0.13

izik

-0.13

ÐµÐ»Ð¸Ðº

-0.13

.Networking

-0.13

 Ð¿Ð¾Ð¿

-0.13

reece

-0.13

POSITIVE LOGITS

 juris

0.29

BA

0.29

Jur

0.29

 bachelor

0.28

 Bachelor

0.28

 doctor

0.26

 Master

0.25

Jur

0.25

 master

0.24

BS

0.24

Activations Density 0.042%

academic qualifications and degrees

No Comments

No Known Activations