INDEX

Explanations

references to mindfulness and mental awareness

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

oste

-0.17

bett

-0.16

oint

-0.15

ost

-0.14

edo

-0.14

ritz

-0.14

usercontent

-0.14

anta

-0.14

PKG

-0.14

ureka

-0.14

POSITIVE LOGITS

fulness

0.29

fully

0.25

ustry

0.24

FUL

0.23

 blown

0.21

 blowing

0.20

/body

0.19

lessly

0.19

meld

0.19

sets

0.18

Activations Density 0.015%

references to mindfulness and mental awareness

No Comments

No Known Activations