INDEX

Explanations

terms and strategies related to gaming mechanics and encounters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

omik

-0.16

 haus

-0.14

wers

-0.13

 competing

-0.13

lesen

-0.13

ucha

-0.13

Abr

-0.13

 gezocht

-0.13

 settle

-0.13

POSITIVE LOGITS

HP

0.22

 health

0.22

hp

0.21

 ranged

0.21

HP

0.21

 Health

0.20

-health

0.20

mob

0.20

Health

0.20

health

0.19

Activations Density 0.177%

terms and strategies related to gaming mechanics and encounters

No Comments

No Known Activations