INDEX

Explanations

references to legal practices and services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

yÅ¡

-0.17

/legal

-0.17

 Lawyers

-0.17

é¼

-0.16

 Ð·Ð°ÐºÐ¾Ð½Ð¾Ð¼

-0.16

æ³ķéĻ¢

-0.16

 Lawyer

-0.15

 lawyers

-0.15

jur

-0.15

 lawyer

-0.15

POSITIVE LOGITS

 civil

0.25

 Admir

0.24

 estate

0.23

 admir

0.23

 tort

0.23

 commercial

0.23

 Estate

0.23

 real

0.22

 immigration

0.21

 workers

0.21

Activations Density 0.139%

references to legal practices and services

No Comments

No Known Activations