INDEX

Explanations

technical coding terms related to game events and player interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

æħ§

-0.14

 product

-0.13

 hurd

-0.12

 Rays

-0.12

 bouncing

-0.12

 action

-0.12

 Chargers

-0.12

MMA

-0.12

 Slip

-0.12

housing

-0.12

POSITIVE LOGITS

 Score

0.37

Score

0.36

score

0.35

 Players

0.35

_score

0.34

 Player

0.34

 Scores

0.34

 score

0.34

Player

0.34

 player

0.33

Activations Density 0.037%

technical coding terms related to game events and player interactions

No Comments

No Known Activations