INDEX

Explanations

text that discusses introductions and new beginnings in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

okable

-0.16

ØªØ§Ø¨

-0.15

 another

-0.14

avra

-0.13

EndDate

-0.13

Ø§ÙĪÛĮ

-0.13

 EXPORT

-0.13

:selected

-0.12

icol

-0.12

awi

-0.12

POSITIVE LOGITS

 introduction

1.02

 introdu

1.00

 Introduction

0.89

 intro

0.87

 introduce

0.82

Introduction

0.81

 Intro

0.79

 introductory

0.79

 introducing

0.77

intro

0.76

Activations Density 0.564%

text that discusses introductions and new beginnings in various contexts

No Comments

No Known Activations