INDEX

Explanations

mentions of Nobel Prizes and their recipients

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 Rating

-0.17

ISO

-0.15

 ÙĤÙħ

-0.15

-rating

-0.15

utra

-0.15

iland

-0.15

eteria

-0.14

æĽ¸é¤¨

-0.14

 Ratings

-0.14

mouth

-0.14

POSITIVE LOGITS

 Nobel

0.30

 laure

0.21

 Laure

0.20

 awarded

0.18

 Citation

0.18

 award

0.18

 citation

0.17

 winner

0.17

Award

0.17

 Prize

0.16

Activations Density 0.043%

mentions of Nobel Prizes and their recipients

No Comments

No Known Activations