INDEX

Explanations

terms related to game mechanics and strategy

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

 dopad

-0.16

lisi

-0.15

Ŀi

-0.15

 seins

-0.14

enty

-0.14

ulumi

-0.14

NF

-0.14

uÃŃ

-0.14

innacle

-0.14

HEMA

-0.13

POSITIVE LOGITS

 buildings

0.31

 building

0.28

building

0.26

build

0.24

 Buildings

0.24

 Building

0.24

-building

0.23

 build

0.23

(build

0.21

 upgrade

0.20

Activations Density 0.058%

terms related to game mechanics and strategy

No Comments

No Known Activations