INDEX

Explanations

key terms related to word searches 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 @ 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

 Corpus

-0.15

Desk

-0.14

McA

-0.13

Ð¾Ð²Ð¾ÑĢ

-0.13

EMA

-0.13

apiro

-0.12

lfw

-0.12

 limestone

-0.12

 shopping

-0.12

 fucking

-0.12

POSITIVE LOGITS

 sudoku

0.32

 Sudoku

0.32

 puzzle

0.27

udoku

0.26

 puzzles

0.25

 Puzzle

0.24

 clues

0.24

 solver

0.23

 clue

0.23

 elim

0.23

Activations Density 0.009%

key terms related to word searches and puzzles

No Comments

No Known Activations