INDEX

Explanations

references to knowledge, awareness, and information sharing

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

idUser

-0.17

ucha

-0.16

acco

-0.15

directive

-0.15

Ð¾ÑĤÑĮ

-0.14

Ø°

-0.14

rack

-0.14

-des

-0.13

beits

-0.13

à¥ģà¤®

-0.13

POSITIVE LOGITS

 about

0.23

 ráº±ng

0.19

&action

0.18

About

0.18

omba

0.18

how

0.16

about

0.16

 About

0.16

 bahwa

0.16

 tentang

0.16

Activations Density 0.253%

references to knowledge, awareness, and information sharing

No Comments

No Known Activations