INDEX

Explanations

concepts related to scientific variables and their relationships

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

Ãłnh

-0.15

ilim

-0.15

 Swift

-0.15

¾

-0.14

 Mant

-0.14

 prem

-0.14

edn

-0.14

INAL

-0.14

ç¯Ģ

-0.14

Ã¼lÃ¼

-0.14

POSITIVE LOGITS

 quantum

0.32

 Quantum

0.29

 wave

0.23

 deco

0.22

Boh

0.22

collapse

0.21

openhagen

0.21

 Copenhagen

0.21

 Everett

0.20

 pointer

0.20

Activations Density 0.058%

concepts related to scientific variables and their relationships

No Comments

No Known Activations