INDEX

Explanations

technical terms and parameters related to machine learning algorithms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

quine

-0.16

rist

-0.15

 segmented

-0.15

arget

-0.14

å¿Ļ

-0.14

uddy

-0.14

LBL

-0.14

 bullet

-0.13

erten

-0.13

 bullets

-0.13

POSITIVE LOGITS

 kernel

0.23

 conv

0.23

 layers

0.23

 layer

0.22

conv

0.22

 Layer

0.22

 pooling

0.22

/kernel

0.21

 Conv

0.21

 filters

0.20

Activations Density 0.001%

technical terms and parameters related to machine learning algorithms

No Comments

No Known Activations