INDEX

Explanations

updates and announcements about new content or resources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

-0.15

ãĥ©ãĤ¤ãĥĪ

-0.13

rokes

-0.13

engkap

-0.13

prior

-0.13

 Hlav

-0.13

brands

-0.13

.credit

-0.13

 pros

-0.13

 topLeft

-0.13

POSITIVE LOGITS

 finally

0.24

 update

0.22

new

0.20

finally

0.19

 Finally

0.19

 updates

0.18

 today

0.18

 newest

0.17

ei

0.17

 final

0.17

Activations Density 0.224%

updates and announcements about new content or resources

No Comments

No Known Activations