INDEX

Explanations

terms related to quantum physics and electronic models

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

ouve

-0.15

_SHARE

-0.15

repid

-0.14

ixels

-0.14

endar

-0.14

Hyper

-0.14

-widget

-0.14

geom

-0.13

ixon

-0.13

jsc

-0.13

POSITIVE LOGITS

 hole

0.27

-hole

0.26

 Hubbard

0.26

 Hole

0.25

hole

0.24

 excit

0.24

 Cooper

0.23

 holes

0.22

 pairing

0.22

 particle

0.21

Activations Density 0.010%

terms related to quantum physics and electronic models

No Comments

No Known Activations