INDEX

Explanations

references to customization and personalization options for products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

coni

-0.17

alette

-0.16

andex

-0.15

 tarif

-0.15

rated

-0.15

rote

-0.15

NSNotification

-0.15

esterday

-0.14

ë¶

-0.14

bindings

-0.14

POSITIVE LOGITS

 personal

0.29

 Personal

0.28

personal

0.25

 personalize

0.24

 laser

0.24

Personal

0.24

 Laser

0.21

 personalized

0.20

 option

0.20

las

0.20

Activations Density 0.058%

references to customization and personalization options for products

No Comments

No Known Activations