INDEX

Explanations

legal jargon and references to court decisions

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

istrovstvÃŃ

-0.13

 Techniques

-0.12

 Hardware

-0.12

artner

-0.12

 Analyzer

-0.11

illac

-0.11

ÙĬÙħØ©

-0.11

Î»Î¿

-0.11

 Armor

-0.11

reator

-0.11

POSITIVE LOGITS

 Statement

0.41

Statement

0.39

 Speech

0.37

 statement

0.37

 Remarks

0.35

 Letter

0.34

Speech

0.33

 speech

0.32

 Statements

0.32

_statement

0.31

Activations Density 0.152%

legal jargon and references to court decisions

No Comments

No Known Activations