INDEX

Explanations

instances of individuals recognized for their foundational or leading roles in various contexts

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

½æķ°

-0.15

ä¸Ŀ

-0.14

ritt

-0.14

owler

-0.14

èĩ£

-0.14

enden

-0.13

ataire

-0.13

 subt

-0.13

Ð½ÐºÐ°

-0.13

POSITIVE LOGITS

 brains

0.39

 driving

0.39

brains

0.32

 brain

0.31

 force

0.31

 inst

0.30

 behind

0.29

 Driving

0.28

 architect

0.28

brain

0.26

Activations Density 0.121%

instances of individuals recognized for their foundational or leading roles in various contexts

No Comments

No Known Activations