INDEX

Explanations

terms related to the production or creation of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

rd

-0.16

cie

-0.15

Ø©

-0.15

od

-0.15

iw

-0.15

ngo

-0.14

party

-0.14

leigh

-0.14

per

-0.14

ably

-0.14

POSITIVE LOGITS

oftware

0.17

0.15

abis

0.15

 dara

0.15

lÃ¡n

0.14

ration

0.14

rowse

0.14

Ã¼ven

0.14

.unsplash

0.14

VRT

0.14

Activations Density 0.043%

terms related to the production or creation of something

No Comments

No Known Activations