INDEX

Explanations

phrases indicating companionship or support

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

essaging

-0.17

"crypto

-0.14

UTION

-0.14

tero

-0.14

ergy

-0.14

avez

-0.14

ibling

-0.13

à¹īà¸ĩ

-0.13

'),('

-0.13

º

-0.13

POSITIVE LOGITS

 accompanying

0.19

 accompany

0.19

 accompanies

0.17

ä¼´

0.16

 companion

0.16

 acompaÃ±

0.16

orsch

0.15

 accompagn

0.15

Ã¶m

0.15

 backdrop

0.14

Activations Density 0.206%

phrases indicating companionship or support

No Comments

No Known Activations