INDEX

Explanations

references to lions and related terms within various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

undry

-0.21

alian

-0.16

anson

-0.15

ipv

-0.15

 rope

-0.15

urent

-0.15

alon

-0.14

ÑĥÐ»Ð°

-0.14

neck

-0.14

ustin

-0.14

POSITIVE LOGITS

ess

0.32

esses

0.32

cub

0.24

ardo

0.23

 lion

0.23

 Lion

0.23

el

0.22

ESS

0.21

 mane

0.20

elles

0.20

Activations Density 0.011%

references to lions and related terms within various contexts

No Comments

No Known Activations