INDEX

Explanations

terms associated with technical and engineering concepts, specifically in the context of simulations and system designs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 Alman

-0.14

 measure

-0.14

igel

-0.14

onomies

-0.14

Locker

-0.14

 husband

-0.14

áº¹n

-0.13

fon

-0.13

 domic

-0.13

Fog

-0.13

POSITIVE LOGITS

FE

0.24

 Finite

0.24

 finite

0.23

 simulation

0.23

FE

0.22

 solver

0.22

 Simulation

0.21

æľīéĻĲ

0.21

fea

0.21

 analyses

0.21

Activations Density 0.019%

terms associated with technical and engineering concepts, specifically in the context of simulations and system designs

No Comments

No Known Activations