INDEX

Explanations

technical terms related to machine learning and data processing

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

alue

-0.18

erland

-0.16

election

-0.15

Bond

-0.15

ADDE

-0.14

bond

-0.14

roe

-0.14

ë°ķ

-0.14

 raster

-0.14

quina

-0.14

POSITIVE LOGITS

 transfer

0.23

 domain

0.23

 Transfer

0.21

 Domain

0.20

Domain

0.20

Transfer

0.20

transfer

0.20

 transferred

0.19

 transferring

0.19

 transfers

0.19

Activations Density 0.003%

technical terms related to machine learning and data processing

No Comments

No Known Activations