INDEX

Explanations

technical terms related to sensors and robotics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

chas

-0.17

PLEX

-0.17

roz

-0.16

ivre

-0.14

LOPT

-0.14

ape

-0.14

amo

-0.14

ATOM

-0.13

paque

-0.13

POSITIVE LOGITS

gy

0.37

 gyro

0.30

 heading

0.30

Gy

0.29

gy

0.28

 acceler

0.28

 sensor

0.28

 Heading

0.27

Heading

0.27

 Acceler

0.25

Activations Density 0.020%

technical terms related to sensors and robotics

No Comments

No Known Activations