INDEX

Explanations

numerical trends and statistics in data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

anel

-0.15

oth

-0.15

hev

-0.15

ombo

-0.15

ing

-0.14

finger

-0.14

 å¯Į

-0.14

ody

-0.14

POSITIVE LOGITS

 ÙħÛĮÙĦØ§Ø¯ÛĮ

0.22

 edition

0.20

Ø¡

0.18

edition

0.18

-present

0.17

âĢ³

0.17

 editions

0.16

 https

0.15

letion

0.15

elden

0.15

Activations Density 0.127%

numerical trends and statistics in data

No Comments

No Known Activations