INDEX

Explanations

elements related to introductions and beginnings of discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ivia

-0.15

åıİ

-0.14

ooter

-0.14

hani

-0.13

Ø§ÙĪÛĮ

-0.13

ØªØ§Ø¨

-0.13

jid

-0.13

 Doyle

-0.13

ëł¬

-0.12

avra

-0.12

POSITIVE LOGITS

 introduction

1.15

 introdu

1.10

 Introduction

1.01

 intro

0.93

Introduction

0.93

 introduce

0.93

 introduced

0.88

 introducing

0.85

 Intro

0.84

 introductory

0.81

Activations Density 0.364%

elements related to introductions and beginnings of discussions

No Comments

No Known Activations