INDEX

Explanations

legal terminology and references to statutes or regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

Contours

-0.15

ÑĪÑĤ

-0.13

avra

-0.13

_vars

-0.13

KHTML

-0.13

ä»Ĭ

-0.13

ubu

-0.12

Î»Ïİ

-0.12

Įĵ

-0.12

 washing

-0.12

POSITIVE LOGITS

 section

0.59

 Section

0.58

Section

0.51

section

0.49

_section

0.45

 Sections

0.45

 Article

0.44

-section

0.43

 sections

0.43

.section

0.40

Activations Density 0.453%

legal terminology and references to statutes or regulations

No Comments

No Known Activations