INDEX

Explanations

references to locations and landmarks in Washington, DC

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 Auckland

-0.19

 Manitoba

-0.17

oÅĻ

-0.15

YY

-0.15

rych

-0.15

vincial

-0.15

 electro

-0.15

 statewide

-0.15

 Sabha

-0.15

ucene

-0.14

POSITIVE LOGITS

 Washington

0.50

DC

0.50

Washington

0.47

 washington

0.44

DC

0.43

 Redskins

0.43

ashington

0.39

dc

0.39

WASHINGTON

0.37

.dc

0.37

Activations Density 0.312%

references to locations and landmarks in Washington, DC

No Comments

No Known Activations