INDEX

Explanations

mathematical symbols and notation related to field theories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

chine

-0.16

nel

-0.15

uib

-0.15

 agendas

-0.14

ntag

-0.14

acea

-0.14

lint

-0.13

gam

-0.13

lio

-0.13

POSITIVE LOGITS

 masses

0.21

 Vacuum

0.21

vac

0.20

 bare

0.19

 spontaneous

0.18

 Bare

0.18

 scalar

0.18

 Scalars

0.17

vac

0.17

 vacc

0.17

Activations Density 0.013%

mathematical symbols and notation related to field theories

No Comments

No Known Activations