INDEX

Explanations

references to Nietzsche and his philosophical concepts related to understanding and knowledge

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

-0.17

Merc

-0.16

Ð´Ð°ÑĤ

-0.15

ãĥ¢ãĥ³

-0.15

 Merc

-0.15

udder

-0.15

acob

-0.14

olumn

-0.14

elli

-0.14

 Sherlock

-0.14

POSITIVE LOGITS

 Wagner

0.26

 Pars

0.24

Zar

0.22

 Tristan

0.22

 Niet

0.22

 Mime

0.21

Sie

0.21

 Dion

0.19

Nib

0.18

 Ring

0.18

Activations Density 0.016%

references to Nietzsche and his philosophical concepts related to understanding and knowledge

No Comments

No Known Activations