INDEX

Explanations

technical terminology related to quantum mechanics and energy spectra

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 Stanton

-0.15

mÄĽ

-0.14

rowad

-0.14

.Loader

-0.14

éĴŁ

-0.13

riv

-0.13

 scalar

-0.13

oval

-0.13

 congress

-0.13

POSITIVE LOGITS

 scales

0.32

 regime

0.26

 regimes

0.24

typ

0.23

 typical

0.22

cales

0.21

 characteristic

0.21

 scale

0.21

Characteristic

0.20

stagram

0.19

Activations Density 0.127%

technical terminology related to quantum mechanics and energy spectra

No Comments

No Known Activations