INDEX

Explanations

references to data types and their properties in programming contexts, particularly focusing on boolean and numeric types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ooks

-0.15

lessly

-0.15

dek

-0.15

ultz

-0.14

ooter

-0.14

edl

-0.13

dic

-0.13

peater

-0.13

LocalizedString

-0.13

loff

-0.13

POSITIVE LOGITS

0.33

0.29

/int

0.24

egers

0.23

0.22

åŀĭ

0.22

.MaxValue

0.22

.MinValue

0.22

.Parse

0.21

Activations Density 0.096%

references to data types and their properties in programming contexts, particularly focusing on boolean and numeric types

No Comments

No Known Activations