INDEX

Explanations

phrases relating to user input and account management

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

ipop

-0.14

rsa

-0.14

isay

-0.14

.opend

-0.13

.files

-0.13

igh

-0.13

aida

-0.13

/history

-0.13

iat

-0.13

Certificates

-0.13

POSITIVE LOGITS

 details

0.29

 name

0.25

 serial

0.25

 username

0.24

 code

0.23

 address

0.22

 valid

0.22

details

0.21

ID

0.21

 email

0.21

Activations Density 0.138%

phrases relating to user input and account management

No Comments

No Known Activations