INDEX

Explanations

phrases and concepts related to differing perspectives or sides of an issue

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

avit

-0.15

amat

-0.15

indr

-0.14

ConverterFactory

-0.14

argas

-0.14

Ø¹ÙĬ

-0.14

omination

-0.14

onto

-0.14

à¸±à¸Ķà¸ª

-0.14

POSITIVE LOGITS

 spectrum

0.34

 aisle

0.29

 coin

0.28

 equation

0.27

 fence

0.27

 Spectrum

0.24

 divide

0.24

coin

0.22

_spectrum

0.21

pectrum

0.21

Activations Density 0.038%

phrases and concepts related to differing perspectives or sides of an issue

No Comments

No Known Activations