INDEX

Explanations

terms related to patents and legal definitions

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

wd

-0.15

âĢ¦↵↵↵

-0.15

udad

-0.14

 VÃ¡c

-0.14

ihan

-0.14

ostel

-0.14

aption

-0.14

Åĳs

-0.13

Colour

-0.13

 Suitable

-0.13

POSITIVE LOGITS

 âĢº

0.34

Pat

0.27

US

0.27

.US

0.25

 Forms

0.23

âĢº

0.23

 Lawyer

0.22

 patents

0.21

Pat

0.20

 Trad

0.20

Activations Density 0.003%

terms related to patents and legal definitions

No Comments

No Known Activations