INDEX

Explanations

acknowledgments of funding and contributions in research documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

braco

-0.17

oxel

-0.15

-follow

-0.15

znik

-0.15

.pb

-0.14

followers

-0.14

Ã²i

-0.14

.mods

-0.14

 tomorrow

-0.14

uffix

-0.14

POSITIVE LOGITS

 acknowledge

0.26

 acknowledges

0.24

 financial

0.23

 acknowledgment

0.22

 funding

0.22

 grate

0.22

 acknow

0.22

unding

0.21

 partial

0.20

 Funding

0.20

Activations Density 0.033%

acknowledgments of funding and contributions in research documents

No Comments

No Known Activations