INDEX

Explanations

phrases indicating ownership or personalization

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 himself

-0.17

ikal

-0.17

 herself

-0.17

inta

-0.16

disk

-0.15

INARY

-0.15

unts

-0.14

 bÃŃ

-0.14

ous

-0.14

 Mond

-0.14

POSITIVE LOGITS

udy

0.16

aly

0.15

url

0.15

éĶ

0.15

ERGY

0.14

sworth

0.14

version

0.14

URL

0.14

 version

0.14

erner

0.14

Activations Density 0.039%

phrases indicating ownership or personalization

No Comments

No Known Activations