INDEX

Explanations

references to game mechanics and design elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

otope

-0.15

ehir

-0.13

çµ¡

-0.13

parer

-0.13

ponde

-0.13

 Lage

-0.13

arts

-0.13

icket

-0.13

à¥įà¤¤à¤ķ

-0.12

ihan

-0.12

POSITIVE LOGITS

 players

1.12

 player

1.11

 Players

0.97

 Player

0.90

player

0.86

-player

0.85

players

0.84

Players

0.83

Player

0.82

_player

0.75

Activations Density 0.237%

references to game mechanics and design elements

No Comments

No Known Activations