INDEX

Explanations

references to literature and book-related content

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

 Empresa

-0.11

 equipments

-0.11

çĽ´æĴŃ

-0.11

ImageContext

-0.11

 Webcam

-0.11

à¹Īà¸Ļ

-0.10

 vidÃ©os

-0.10

è§Ĥçľĭ

-0.10

 Aluminium

-0.10

à¸Ľà¸£à¸°à¸Ĭ

-0.10

POSITIVE LOGITS

 books

0.52

 novels

0.50

 book

0.50

 paperback

0.49

 literary

0.48

 Books

0.47

 publishers

0.45

 publishing

0.44

 Literary

0.44

 authors

0.44

Activations Density 3.496%

references to literature and book-related content

No Comments

No Known Activations