INDEX

Explanations

references to Buddhist concepts and figures

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

itia

-0.16

êµĲíļĮ

-0.14

_ROM

-0.14

/ion

-0.14

aleb

-0.13

/rfc

-0.13

coni

-0.13

obil

-0.13

 Antony

-0.13

bib

-0.13

POSITIVE LOGITS

 Buddha

0.41

 Budd

0.35

 Buddhist

0.34

 Buddhism

0.34

 budd

0.33

 Buddh

0.32

Bod

0.31

 Ther

0.31

 monks

0.31

Bud

0.31

Activations Density 0.025%

references to Buddhist concepts and figures

No Comments

No Known Activations