INDEX

Explanations

references to word games and puzzles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

lfw

-0.17

LocalizedString

-0.15

 Jacobs

-0.15

.MixedReality

-0.14

nou

-0.14

 hala

-0.14

witter

-0.14

Ð²Ð°Ð¹

-0.14

ÎºÎ¿

-0.13

quat

-0.13

POSITIVE LOGITS

 elim

0.25

 cell

0.25

 cells

0.24

 sudoku

0.23

 Sudoku

0.23

-cell

0.22

udoku

0.21

 candidates

0.21

 Cell

0.21

 naked

0.21

Activations Density 0.002%

references to word games and puzzles

No Comments

No Known Activations