INDEX

Explanations

technical details related to robotics and automated systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 alarm

-0.17

agli

-0.16

isz

-0.16

 Jennings

-0.16

.scalablytyped

-0.15

Alarm

-0.15

alarm

-0.15

izont

-0.14

cq

-0.14

slideDown

-0.14

POSITIVE LOGITS

 Depth

0.24

 Kinect

0.23

 depth

0.23

ToF

0.23

Depth

0.22

depth

0.22

Lid

0.21

_depth

0.20

.depth

0.20

 lasers

0.19

Activations Density 0.024%

technical details related to robotics and automated systems

No Comments

No Known Activations