INDEX

Explanations

programming and coding concepts related to text formatting and character encoding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 hale

-0.15

 Brew

-0.15

atel

-0.15

ç´ł

-0.14

 Ð¿ÐµÑĢÐµÐ³

-0.14

yped

-0.14

Dev

-0.14

aes

-0.13

±

-0.13

POSITIVE LOGITS

newline

0.27

 newline

0.26

 vbCrLf

0.24

 Lines

0.24

 endl

0.24

 lines

0.23

 Line

0.22

æį¢

0.22

.newLine

0.22

lines

0.21

Activations Density 0.071%

programming and coding concepts related to text formatting and character encoding

No Comments

No Known Activations