INDEX

Explanations

concepts related to gameplay mechanics and character abilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

orum

-0.15

stab

-0.14

outil

-0.14

 recl

-0.14

abal

-0.14

.bukkit

-0.14

 folds

-0.14

brig

-0.14

 AUTHORS

-0.14

POSITIVE LOGITS

 Dialogue

0.17

 enemies

0.16

 puzzles

0.16

 door

0.15

 timed

0.15

 tutorial

0.15

 puzzle

0.15

ileo

0.14

 collect

0.14

EGA

0.14

Activations Density 0.071%

concepts related to gameplay mechanics and character abilities

No Comments

No Known Activations