INDEX

Explanations

elements related to guidelines and regulations

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

lash

-0.15

mpp

-0.14

ç»ĩ

-0.13

ypo

-0.13

yan

-0.13

leh

-0.13

ÏĥÎ¹Î¿

-0.13

Ð½Ð¸Ð½Ð°

-0.13

æ¿Ģ

-0.13

Installed

-0.13

POSITIVE LOGITS

 guidance

0.41

 Guidance

0.36

 guid

0.31

Guid

0.30

guid

0.30

 guides

0.29

 Guid

0.28

 guide

0.28

 GUID

0.27

 Guide

0.26

Activations Density 0.196%

elements related to guidelines and regulations

No Comments

No Known Activations