INDEX

Explanations

references to legal language and concepts related to legislation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ault

-0.14

alon

-0.14

-badge

-0.14

seud

-0.14

ç»ĥ

-0.13

 Laws

-0.13

 é¢

-0.13

è¾ħ

-0.13

bu

-0.13

POSITIVE LOGITS

 language

0.49

language

0.40

 Language

0.37

 provision

0.36

 wording

0.35

 provisions

0.34

Language

0.34

 LANGUAGE

0.31

 lang

0.30

-language

0.28

Activations Density 0.198%

references to legal language and concepts related to legislation

No Comments

No Known Activations