INDEX

Explanations

specific proper nouns and titles related to various cultural, political, and social contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ÅĻÃŃd

-0.16

Ã¼st

-0.15

idunt

-0.15

istrovstvÃŃ

-0.15

Languages

-0.15

itary

-0.14

jury

-0.14

loÅ¾

-0.14

liest

-0.14

'gc

-0.14

POSITIVE LOGITS

ocene

0.17

zheimer

0.17

bes

0.16

zier

0.15

åıĭ

0.14

avian

0.13

 prec

0.13

/Edit

0.13

/C

0.13

Activations Density 0.534%

specific proper nouns and titles related to various cultural, political, and social contexts

No Comments

No Known Activations