INDEX

Explanations

keywords related to openness and open environments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Opening

-0.25

 Opening

-0.24

opening

-0.23

 opening

-0.20

 opener

-0.20

-opening

-0.19

 opened

-0.18

 Opens

-0.18

 opens

-0.17

opens

-0.17

POSITIVE LOGITS

-ended

0.38

-air

0.33

 ended

0.32

ended

0.30

Ended

0.27

 Ended

0.27

-source

0.25

baar

0.25

air

0.24

-plan

0.24

Activations Density 0.031%

keywords related to openness and open environments

No Comments

No Known Activations