INDEX

Explanations

technical terms related to atomic interactions and ionization processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

æµª

-0.17

nger

-0.16

dat

-0.15

éļĨ

-0.14

fish

-0.14

 Fist

-0.14

 Stein

-0.13

Loc

-0.13

 Punch

-0.13

Ð½ÑĸÐ²

-0.13

POSITIVE LOGITS

 trap

0.25

Ry

0.25

 atoms

0.24

 atomic

0.24

 traps

0.23

MOT

0.23

 atom

0.22

 Atom

0.22

 Ramsey

0.22

Trap

0.22

Activations Density 0.004%

technical terms related to atomic interactions and ionization processes

No Comments

No Known Activations