INDEX

Explanations

technical terms and measurements related to scientific studies

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

atrix

-0.17

ÏĢÎ¬

-0.15

oles

-0.15

orda

-0.14

omap

-0.14

ÏĦÏİ

-0.14

ropdown

-0.14

illy

-0.14

ìĸĳ

-0.13

æĻ¯

-0.13

POSITIVE LOGITS

 accuracy

0.51

 precision

0.47

 Accuracy

0.43

 Precision

0.40

accuracy

0.40

 accur

0.39

 error

0.39

 tolerance

0.36

Accuracy

0.35

Precision

0.35

Activations Density 0.138%

technical terms and measurements related to scientific studies

No Comments

No Known Activations