INDEX

Explanations

proper nouns and names associated with the entertainment and media industry

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ung

-0.16

unga

-0.16

apest

-0.16

ialias

-0.15

er

-0.15

ores

-0.15

isel

-0.15

 Lazar

-0.14

 Moss

-0.13

POSITIVE LOGITS

íĭ±

0.16

-FIRST

0.15

AGIC

0.14

à¥ģà¤Ĺà¤¤

0.14

 DEALINGS

0.14

jec

0.14

Caption

0.14

marked

0.14

znik

0.13

 ders

0.13

Activations Density 0.023%

proper nouns and names associated with the entertainment and media industry

No Comments

No Known Activations