INDEX

Explanations

terminology and concepts related to nuclear physics and particles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

enco

-0.17

 Prov

-0.14

/pkg

-0.14

 Emperor

-0.14

 Spinner

-0.14

indle

-0.14

PCODE

-0.13

ãĥ¼ãĥª

-0.13

å¤ķ

-0.13

.wind

-0.13

POSITIVE LOGITS

 collider

0.23

TeV

0.23

 accelerator

0.20

 collisions

0.20

CMS

0.20

upgrade

0.18

daq

0.18

 beam

0.18

 Upgrade

0.18

Upgrade

0.18

Activations Density 0.004%

terminology and concepts related to nuclear physics and particles

No Comments

No Known Activations