INDEX

Explanations

punctuation marks and formatting symbols frequently used in technical discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ten

-0.27

TEN

-0.25

Ten

-0.25

Ten

-0.24

ten

-0.23

-0.22

Û±Û°

-0.22

_ten

-0.20

ï¼ĳï¼Ĳ

-0.19

-0.18

POSITIVE LOGITS

0.52

0.48

0.38

 fourteen

0.37

XIV

0.36

 fifteen

0.33

åįģåĽĽ

0.32

Û±Û´

0.31

åįģäºĶ

0.31

Activations Density 0.050%

punctuation marks and formatting symbols frequently used in technical discussions

No Comments

No Known Activations