INDEX

Explanations

references to technical specifications or codes related to products or systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

 dist

-0.15

Ã¢k

-0.14

è³¢

-0.14

yes

-0.13

ilig

-0.13

 cycl

-0.13

Ngh

-0.13

åµ

-0.13

/cms

-0.13

 Oliv

-0.13

POSITIVE LOGITS

Ð»Ð¸Ð½Ð°

0.17

getc

0.16

annie

0.16

iju

0.15

assin

0.15

isko

0.15

ushima

0.14

 nomine

0.14

linger

0.14

cel

0.14

Activations Density 0.627%

references to technical specifications or codes related to products or systems

No Comments

No Known Activations