INDEX

Explanations

phrases expressing commitment or ongoing involvement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 itself

-0.23

æĪĳçļĦ

-0.21

 meiner

-0.17

 saya

-0.17

ç»ĻæĪĳ

-0.17

 minha

-0.16

meu

-0.16

 meine

-0.15

my

-0.15

 mijn

-0.15

POSITIVE LOGITS

 ourselves

0.36

 talking

0.26

 fortunate

0.22

 lucky

0.22

 told

0.21

 mere

0.20

 hearing

0.20

 seeing

0.20

 living

0.19

fortunate

0.19

Activations Density 0.104%

phrases expressing commitment or ongoing involvement

No Comments

No Known Activations