INDEX

Explanations

elements related to numerical values, measurements, and financial figures

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

-0.23

oric

-0.16

eldom

-0.15

ob

-0.15

illiseconds

-0.14

ieber

-0.14

shal

-0.14

avr

-0.14

à¸Ļà¸Ń

-0.13

itos

-0.13

POSITIVE LOGITS

.tw

0.29

fort

0.28

twenty

0.26

 twenty

0.24

 thirty

0.22

nin

0.22

 forty

0.22

äºĮåįģ

0.21

_tw

0.20

 eighty

0.20

Activations Density 0.352%

elements related to numerical values, measurements, and financial figures

No Comments

No Known Activations