INDEX

Explanations

titles of books and stories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ABOUT

-0.17

plements

-0.16

èĢģ

-0.15

asca

-0.15

ss

-0.15

 Macros

-0.15

ierrez

-0.15

ÐµÐ¿ÑĤÐ¸

-0.14

 ABOUT

-0.14

imb

-0.14

POSITIVE LOGITS

arto

0.18

olut

0.15

Ð»Ð¸Ðº

0.15

 Wenger

0.15

 vá»¥

0.15

ypy

0.14

upy

0.14

otal

0.14

 fisse

0.14

ittel

0.14

Activations Density 0.036%

titles of books and stories

No Comments

No Known Activations