INDEX

Explanations

conditional phrases suggesting potential outcomes or actions

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

loid

-0.15

ovky

-0.15

quier

-0.15

otti

-0.14

-alist

-0.14

æ»¿

-0.14

æľ

-0.14

ãĥ¼ãĤ¹

-0.14

ipo

-0.14

yon

-0.14

POSITIVE LOGITS

uely

0.17

 awareness

0.17

 appearance

0.17

enthal

0.16

dbus

0.16

appearance

0.15

%M

0.15

chia

0.15

 growth

0.15

 percentage

0.14

Activations Density 0.003%

conditional phrases suggesting potential outcomes or actions

No Comments

No Known Activations