INDEX

Explanations

quantitative data points related to visitors, fatality rates, and organizational meeting metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

pong

-0.16

acey

-0.16

addir

-0.15

lew

-0.14

immel

-0.14

OLON

-0.14

ium

-0.14

.Selenium

-0.14

 Driving

-0.13

umlu

-0.13

POSITIVE LOGITS

 each

0.32

per

0.32

 every

0.30

æ¯ı

0.27

 má»Ĺi

0.25

 æ¯ı

0.25

 annually

0.25

 chaque

0.24

each

0.24

every

0.23

Activations Density 0.131%

quantitative data points related to visitors, fatality rates, and organizational meeting metrics

No Comments

No Known Activations