INDEX

Explanations

references to significant changes or events 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 @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

-0.16

cken

-0.15

BY

-0.15

gem

-0.15

bou

-0.15

å®ļ

-0.15

ushman

-0.15

bou

-0.14

Bou

-0.14

Gem

-0.14

POSITIVE LOGITS

 indem

0.39

 Ð¿ÑĥÑĤÐµÐ¼

0.34

 ÑĪÐ»ÑıÑħÐ¾Ð¼

0.29

 báº±ng

0.28

 tÃŃm

0.27

 thanks

0.23

by

0.23

 à¹Ĥà¸Ķà¸¢

0.19

 mediante

0.18

 grÃ¢ce

0.18

Activations Density 0.574%

references to significant changes or events in various contexts

No Comments

No Known Activations