INDEX

Explanations

references to eyes and vision

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

Aceptar

-0.17

oil

-0.15

 bacheca

-0.15

ystore

-0.15

vla

-0.15

lava

-0.14

yang

-0.14

ILLISE

-0.14

anium

-0.14

èĤĮ

-0.14

POSITIVE LOGITS

 lenses

0.24

 Lens

0.24

Eye

0.22

 Tear

0.22

 tear

0.21

 tears

0.20

eye

0.20

 lens

0.20

phthalm

0.20

Ey

0.19

Activations Density 0.055%

references to eyes and vision

No Comments

No Known Activations

references to eyes and vision

No Comments

No Known Activations