INDEX

Explanations

concepts and terminology related to emotional states and psychological conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 Gund

-0.15

èĻİ

-0.14

 herald

-0.14

 Ministry

-0.13

 sÃ¡ng

-0.13

 chant

-0.13

ÑĥÑĢÐ¸

-0.13

à¸¢à¸ĩ

-0.13

enef

-0.13

æĭĵ

-0.13

POSITIVE LOGITS

 emotion

0.48

 emotions

0.44

emotion

0.39

 emotional

0.35

 Emotional

0.34

 emoc

0.29

emo

0.28

æĥħ

0.28

 emot

0.27

æĦŁæĥħ

0.27

Activations Density 0.109%

concepts and terminology related to emotional states and psychological conditions

No Comments

No Known Activations