INDEX

Explanations

elements related to video game mechanics and features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

eve

-0.14

ÙĦØ³

-0.14

.magic

-0.14

piar

-0.14

è¾°

-0.14

 sacrific

-0.14

lÄ±ÄŁa

-0.13

pered

-0.13

 substitutions

-0.13

POSITIVE LOGITS

 missions

0.40

 mission

0.36

 boss

0.33

 bosses

0.31

missions

0.30

 campaign

0.30

mission

0.29

 Mission

0.28

boss

0.28

 Campaign

0.27

Activations Density 0.163%

elements related to video game mechanics and features

No Comments

No Known Activations