INDEX

Explanations

details related to technical specifications and performance of power supply units

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

Ãºt

-0.17

à¸²à¸ĺ

-0.15

illard

-0.14

osl

-0.14

iyat

-0.14

ãĥ³ãĥĨãĤ£

-0.14

-dismissible

-0.14

ewood

-0.13

 Ð°ÐºÑĤÐ¸

-0.13

icago

-0.13

POSITIVE LOGITS

 power

0.19

 output

0.19

_DC

0.17

 Output

0.17

.AC

0.16

AC

0.15

¢

0.15

.Output

0.15

output

0.15

regulated

0.15

Activations Density 0.034%

details related to technical specifications and performance of power supply units

No Comments

No Known Activations