INDEX

Explanations

references to player experiences and game enjoyment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

olas

-0.17

egen

-0.15

icros

-0.14

msgid

-0.14

uliar

-0.14

ä¸²

-0.14

-0.13

upp

-0.13

aguay

-0.13

itu

-0.13

POSITIVE LOGITS

 Resident

0.24

 Bios

0.24

 Border

0.22

 Call

0.22

Nie

0.22

 Mass

0.21

 Plants

0.21

 Civilization

0.21

_Call

0.20

 bios

0.20

Activations Density 0.328%

references to player experiences and game enjoyment

No Comments

No Known Activations