INDEX

Explanations

terms related to game updates and items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ãĤ¸ãĤ¢

-0.14

 Angry

-0.14

ayd

-0.14

Vib

-0.14

å½¦

-0.14

rtle

-0.13

ut

-0.13

sdale

-0.13

á»Ĺng

-0.13

Sno

-0.13

POSITIVE LOGITS

 Souls

0.19

 souls

0.17

 bosses

0.16

ngx

0.16

elda

0.16

lei

0.15

equip

0.15

Equip

0.15

ewire

0.14

Ã¤hr

0.14

Activations Density 0.008%

terms related to game updates and items

No Comments

No Known Activations