INDEX

Explanations

technical terms and jargon related to custom construction and event messaging in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

à¸±à¸ĩà¸ª

-0.15

 Kern

-0.15

onica

-0.14

nech

-0.14

ewood

-0.14

ixa

-0.14

zap

-0.14

ahrain

-0.13

 sourceMapping

-0.12

 Avery

-0.12

POSITIVE LOGITS

ros

0.42

ROS

0.41

ROS

0.35

Ros

0.33

ros

0.33

Ros

0.31

_ros

0.31

/ros

0.30

 rospy

0.27

 publisher

0.27

Activations Density 0.020%

technical terms and jargon related to custom construction and event messaging in programming

No Comments

No Known Activations