INDEX

Explanations

terms related to fractals and their properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ÑĢÐ¸Ðº

-0.15

sy

-0.15

mlin

-0.14

amat

-0.14

unic

-0.14

wik

-0.14

imator

-0.14

Ø³Ø§ÙĨ

-0.14

uhl

-0.14

 Bond

-0.14

POSITIVE LOGITS

IEL

0.15

æľĿ

0.15

ilia

0.15

.imag

0.15

aleur

0.15

enaire

0.14

nÄħ

0.14

 aliqua

0.14

chrono

0.14

ImageSharp

0.14

Activations Density 0.310%

terms related to fractals and their properties

No Comments

No Known Activations