INDEX

Explanations

numbers, dates, and measurements within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

nin

-0.18

-0.17

Nin

-0.15

 sevent

-0.15

 eighty

-0.15

POSITIVE LOGITS

0.83

Û±Û¹Û´

0.56

0.54

Û±Û¹Ûµ

0.40

0.37

 wartime

0.34

 WWII

0.31

 fasc

0.26

war

0.24

 fascism

0.23

Activations Density 0.050%

numbers, dates, and measurements within the text

No Comments

No Known Activations