INDEX

Explanations

elements of patent filing information and classifications

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

zilla

-0.20

abbix

-0.16

aturday

-0.15

loff

-0.14

ividual

-0.14

(éĩĳ

-0.14

azio

-0.14

Ã¨ne

-0.14

amins

-0.13

.startActivity

-0.13

POSITIVE LOGITS

Poz

0.15

%+

0.15

 belt

0.15

 inse

0.14

ffm

0.14

 daily

0.14

Ut

0.13

hed

0.13

 fair

0.13

 born

0.13

Activations Density 0.003%

elements of patent filing information and classifications

No Comments

No Known Activations