INDEX

Explanations

references to the concept of simplicity and effectiveness in expression

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

íĬ¹ë³Ħ

-0.15

ITTE

-0.15

tega

-0.14

-toggler

-0.14

uters

-0.14

ierz

-0.13

ansson

-0.13

tual

-0.13

azzo

-0.13

azor

-0.13

POSITIVE LOGITS

lot

0.31

 majority

0.30

 person

0.26

 lack

0.24

 properly

0.24

LOT

0.23

 curs

0.23

 good

0.21

 glance

0.20

Lot

0.20

Activations Density 0.218%

references to the concept of simplicity and effectiveness in expression

No Comments

No Known Activations