INDEX

Explanations

data related to measurements and performance metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

cean

-0.15

rocket

-0.14

avanaugh

-0.14

ighting

-0.14

Pai

-0.14

aro

-0.14

Ros

-0.13

 Millet

-0.13

agu

-0.13

Ãºb

-0.13

POSITIVE LOGITS

per

0.49

_per

0.37

-per

0.34

per

0.31

Per

0.30

Per

0.29

/sec

0.28

_PER

0.27

.per

0.26

/min

0.25

Activations Density 0.105%

data related to measurements and performance metrics

No Comments

No Known Activations