INDEX

Explanations

references to educational courses and teaching activities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

assa

-0.17

vla

-0.15

 maths

-0.14

ileo

-0.14

.mit

-0.14

 mathematic

-0.14

.dtd

-0.14

ediÄŁi

-0.14

 Maths

-0.14

imeo

-0.14

POSITIVE LOGITS

 Introduction

0.37

 Intro

0.34

Introduction

0.33

 intro

0.32

 introduction

0.31

 introductory

0.31

Intro

0.30

 Advanced

0.29

 advanced

0.28

 introdu

0.28

Activations Density 0.060%

references to educational courses and teaching activities

No Comments

No Known Activations