INDEX

Explanations

terms associated with interdisciplinary research and methodologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

es

-0.18

æł·çļĦ

-0.17

alt

-0.15

ic

-0.14

-wow

-0.14

ings

-0.14

em

-0.14

el

-0.14

ika

-0.14

pk

-0.14

POSITIVE LOGITS

mente

0.24

ity

0.23

ities

0.20

dehyde

0.19

ypse

0.18

idad

0.18

ness

0.18

¿

0.18

izes

0.17

ITY

0.17

Activations Density 0.912%

terms associated with interdisciplinary research and methodologies

No Comments

No Known Activations