INDEX

Explanations

specific technical terms and programming-related keywords

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

Å¡ov

-0.16

 Mutable

-0.15

á»Ĳ

-0.15

etti

-0.15

ersistent

-0.14

uida

-0.14

 Santo

-0.14

oyer

-0.14

uido

-0.14

Mutable

-0.14

POSITIVE LOGITS

inne

0.22

illo

0.18

yne

0.15

adol

0.15

 contents

0.15

à¸´à¸«à¸²à¸£

0.14

jew

0.14

 Contents

0.14

inine

0.14

ëĤ´

0.14

Activations Density 0.040%

specific technical terms and programming-related keywords

No Comments

No Known Activations