INDEX

Explanations

references to "Nova," indicating a focus on a particular location or organization associated with that name

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

olly

-0.15

ãĤ¹ãĤ³

-0.14

 Kahn

-0.14

.ua

-0.14

ãĥĲãĥ¼

-0.14

yne

-0.14

IFF

-0.14

uez

-0.13

²

-0.13

 trib

-0.13

POSITIVE LOGITS

ledge

0.16

asio

0.15

acer

0.15

 ÙĨØ³Ø¨

0.14

creen

0.14

imitive

0.13

PRETTY

0.13

cly

0.13

Ã¼ck

0.13

 Krish

0.13

Activations Density 0.006%

references to "Nova," indicating a focus on a particular location or organization associated with that name

No Comments

No Known Activations