INDEX

Explanations

specific characters or symbols that represent notable entities or concepts

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

 Lansing

-0.15

 Congressional

-0.15

 Tits

-0.15

CSA

-0.15

KM

-0.14

omor

-0.14

 Architect

-0.14

CSC

-0.14

Viol

-0.14

Porn

-0.14

POSITIVE LOGITS

 Jack

0.31

 Beatles

0.30

 Yesterday

0.27

 McCartney

0.26

 Ellie

0.25

 Lennon

0.24

Jack

0.24

 Boyle

0.24

 Beet

0.24

 Beetle

0.23

Activations Density 0.003%

specific characters or symbols that represent notable entities or concepts

No Comments

No Known Activations