INDEX

Explanations

references to improvisation and its related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ufac

-0.17

 Sweep

-0.16

leccion

-0.16

¹Ħ

-0.15

quests

-0.15

ervas

-0.15

è®¾è®¡åĻ¨

-0.14

 prophet

-0.14

ÐºÑĥÐ»

-0.14

edBy

-0.14

POSITIVE LOGITS

 improvis

0.31

 improv

0.30

 improvised

0.29

 spont

0.28

 spontaneous

0.27

ise

0.27

 spontaneously

0.25

vised

0.24

 Ð¸Ð¼Ð¿

0.23

 Impro

0.23

Activations Density 0.007%

references to improvisation and its related concepts

No Comments

No Known Activations