INDEX

Explanations

references to lions and associated 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 @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

alian

-0.20

undry

-0.19

ipv

-0.18

aign

-0.15

ÙĥØ§Ùħ

-0.15

anson

-0.15

urent

-0.15

ustin

-0.15

sit

-0.15

unik

-0.14

POSITIVE LOGITS

ess

0.33

esses

0.32

cub

0.26

ardo

0.24

fish

0.23

el

0.23

Cub

0.22

 Lion

0.22

 mane

0.22

heart

0.22

Activations Density 0.010%

references to lions and associated terms within various contexts

No Comments

No Known Activations