INDEX

Explanations

words related to legal terms and institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

-0.23

Øª

-0.16

ãĤ¥

-0.15

Ùĩ

-0.15

Ø§ØªÙĩ

-0.14

 endregion

-0.14

-0.13

oples

-0.13

sus

-0.13

allis

-0.13

POSITIVE LOGITS

Ð¼Ð¾Ð²ÑĸÑĢ

0.15

0.14

soever

0.14

soap

0.14

ther

0.14

yc

0.14

)const

0.14

à¥į

0.14

imestep

0.13

ree

0.13

Activations Density 0.121%

words related to legal terms and institutions

No Comments

No Known Activations