INDEX

Explanations

elements related to rankings and hierarchies in gaming contexts

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

caff

-0.18

à¸¥à¸°

-0.17

ubs

-0.15

iou

-0.15

macen

-0.15

ucch

-0.15

ÙĪÙĨÛĮ

-0.15

aiser

-0.15

loub

-0.15

hydrate

-0.15

POSITIVE LOGITS

 Gand

0.31

Bor

0.29

Sar

0.28

Gim

0.28

Fro

0.28

 Merry

0.28

Gal

0.25

Bil

0.25

Leg

0.24

Rad

0.24

Activations Density 0.001%

elements related to rankings and hierarchies in gaming contexts

No Comments

No Known Activations