INDEX

Explanations

queries and discussions related to character classes and gameplay mechanics in role-playing games

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

hsi

-0.16

atte

-0.15

 Workspace

-0.14

bout

-0.14

phin

-0.14

VERR

-0.14

 cuff

-0.14

ÎŃÏģÎ³

-0.14

onto

-0.14

Studio

-0.14

POSITIVE LOGITS

 classes

0.25

 ranger

0.23

 tanks

0.23

subclass

0.22

 tank

0.22

tank

0.21

 tanker

0.21

 Ranger

0.21

 Classes

0.21

_classes

0.20

Activations Density 0.074%

queries and discussions related to character classes and gameplay mechanics in role-playing games

No Comments

No Known Activations