INDEX

Explanations

quotation marks and associated text or dialogue

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

-0.17

aland

-0.14

 Nova

-0.14

amÄ±

-0.14

olland

-0.14

 lectures

-0.14

olit

-0.13

-scalable

-0.13

UZ

-0.13

POSITIVE LOGITS

untas

0.15

Ł

0.15

ikat

0.15

Gain

0.14

.gameserver

0.14

aginator

0.14

izont

0.14

htar

0.14

relude

0.14

Activations Density 0.171%

quotation marks and associated text or dialogue

No Comments

No Known Activations