INDEX

Explanations

references to television shows and their details

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

adol

-0.17

usty

-0.15

PTY

-0.15

earn

-0.14

 Wass

-0.14

eph

-0.14

 Trab

-0.14

èĹĿ

-0.14

hou

-0.14

LOB

-0.13

POSITIVE LOGITS

 Lucifer

0.24

 Agents

0.24

 Transparent

0.23

 Bosch

0.23

NC

0.23

 Vikings

0.22

 Fargo

0.22

 Arrow

0.22

 Homeland

0.22

 Criminal

0.22

Activations Density 0.105%

references to television shows and their details

No Comments

No Known Activations