INDEX

Explanations

phrases related to product qualities and certifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

Äįi

-0.17

idden

-0.17

cak

-0.16

ITT

-0.15

à¤¾à¤

-0.15

.sax

-0.15

?key

-0.15

berger

-0.14

avis

-0.14

ignKey

-0.14

POSITIVE LOGITS

 organic

0.39

 cruelty

0.35

 organ

0.32

 Organic

0.32

organic

0.31

 hypo

0.30

Cru

0.30

 vegan

0.27

 certified

0.24

Organ

0.24

Activations Density 0.118%

phrases related to product qualities and certifications

No Comments

No Known Activations