INDEX

Explanations

technical terms 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 @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

_SMS

-0.15

 simulations

-0.15

 Audit

-0.14

ehr

-0.14

äºĪ

-0.14

å½

-0.14

 Handlers

-0.14

OGLE

-0.14

 Simulator

-0.14

rollo

-0.13

POSITIVE LOGITS

 sensor

0.20

ìĦ¼

0.16

 Sensor

0.16

sensor

0.16

 sensors

0.16

 sensing

0.16

ToF

0.15

ustum

0.15

Outdoor

0.15

 Indoor

0.15

Activations Density 0.053%

technical terms related to robotics and automated systems

No Comments

No Known Activations