INDEX

Explanations

greetings or salutations in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

arra

-0.16

nte

-0.15

åĻ¨

-0.15

éĢļ

-0.14

Î¿ÏħÏĤ

-0.13

.tv

-0.13

furt

-0.13

 parts

-0.13

ube

-0.13

ters

-0.13

POSITIVE LOGITS

ooo

0.26

 everyone

0.24

oooo

0.23

oo

0.23

 everybody

0.23

oooooooo

0.22

 Everyone

0.22

 Kitty

0.22

everyone

0.20

_world

0.20

Activations Density 0.018%

greetings or salutations in the text

No Comments

No Known Activations