INDEX

Explanations

discussions related to game mechanics and bot performance metrics

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

 sims

-0.16

rchive

-0.16

 sublicense

-0.15

å¼¾

-0.15

Colorado

-0.15

brero

-0.15

canf

-0.15

 Colorado

-0.14

GRA

-0.14

Plate

-0.14

POSITIVE LOGITS

 Dota

0.35

DOT

0.32

Dot

0.28

TI

0.28

DOT

0.26

Dot

0.24

 Valve

0.24

 heroes

0.23

 hero

0.23

dot

0.22

Activations Density 0.004%

discussions related to game mechanics and bot performance metrics

No Comments

No Known Activations