INDEX

Explanations

references to law and legal enforcement

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

cassert

-0.19

ugu

-0.18

elocity

-0.17

istor

-0.15

_terminal

-0.15

isode

-0.14

stants

-0.14

Ð¾ÑģÑĮ

-0.14

upert

-0.14

Åº

-0.14

POSITIVE LOGITS

 enforcement

0.49

-en

0.35

enf

0.34

 Enforcement

0.31

en

0.30

men

0.27

 enforce

0.27

 enforcing

0.27

fully

0.24

en

0.23

Activations Density 0.009%

references to law and legal enforcement

No Comments

No Known Activations