INDEX

Explanations

positive descriptions of experiences and activities

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

rire

-0.14

ÐµÑĢÐ¸Ð½

-0.14

isan

-0.13

inde

-0.13

lotte

-0.13

à¤¹à¤°

-0.13

 Reserve

-0.13

Impl

-0.13

minus

-0.13

terra

-0.13

POSITIVE LOGITS

way

0.39

 excuse

0.29

 ways

0.26

 reason

0.25

 opportunity

0.25

 addition

0.24

 place

0.24

WAY

0.24

 chance

0.23

 start

0.22

Activations Density 0.106%

positive descriptions of experiences and activities

No Comments

No Known Activations