INDEX

Explanations

instances of emotional or positive experiences and sentiments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 impecc

-0.14

Äįin

-0.14

ORMAL

-0.14

è¼Ķ

-0.14

 Robbins

-0.14

ÑĦÐ¾ÑĢÐ¼Ð¸

-0.13

.appspot

-0.13

ALK

-0.13

 immac

-0.13

sak

-0.13

POSITIVE LOGITS

 great

0.28

 terr

0.26

 swell

0.25

 Terr

0.25

 GREAT

0.25

Wonder

0.25

 grand

0.25

Great

0.24

great

0.24

 Great

0.23

Activations Density 0.154%

instances of emotional or positive experiences and sentiments

No Comments

No Known Activations