INDEX

Explanations

references to interpersonal dynamics and accountability in relationships

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

à¹Ģà¸Ńà¸ĩ

-0.24

 herself

-0.20

him

-0.20

 myself

-0.19

 sebou

-0.18

 Yourself

-0.18

 mÃ¬nh

-0.17

 Himself

-0.17

 himself

-0.15

tle

-0.15

POSITIVE LOGITS

 peoples

0.38

 their

0.35

 everyone

0.34

 someone

0.33

 somebody

0.33

 everybody

0.32

 your

0.29

his

0.28

 THEIR

0.28

our

0.26

Activations Density 0.675%

references to interpersonal dynamics and accountability in relationships

No Comments

No Known Activations

references to interpersonal dynamics and accountability in relationships

No Comments

No Known Activations