INDEX

Explanations

terms related to game mechanics and abilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

Enemy

-0.15

åľ°çĲĥ

-0.15

eo

-0.14

ä»Ļ

-0.14

ppo

-0.14

/tool

-0.14

 Swords

-0.14

zym

-0.14

æ¨

-0.14

 Sword

-0.14

POSITIVE LOGITS

 sector

0.17

oth

0.16

ivic

0.16

IIC

0.16

 Construct

0.15

 Caller

0.15

ãĥ«ãĥķ

0.15

ollapse

0.14

oken

0.14

-toggler

0.14

Activations Density 0.237%

terms related to game mechanics and abilities

No Comments

No Known Activations