INDEX

Explanations

references to series or sequels in a variety of contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ascript

-0.16

 portions

-0.15

plusplus

-0.15

ÑĤÑİ

-0.14

amine

-0.14

jes

-0.14

 verschied

-0.13

POSITIVE LOGITS

 series

0.32

series

0.26

 serie

0.25

 Ø³ÙĦØ³

0.24

-series

0.23

.series

0.22

 many

0.22

 Series

0.21

 SERIES

0.21

 what

0.21

Activations Density 0.109%

references to series or sequels in a variety of contexts

No Comments

No Known Activations