INDEX

Explanations

references to locations and establishments in New York City

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 Anch

-0.14

 Lean

-0.14

 Metropolitan

-0.14

 beled

-0.14

 California

-0.14

kup

-0.14

Philadelphia

-0.13

 Extras

-0.13

 Philadelphia

-0.13

cod

-0.13

POSITIVE LOGITS

 downtown

0.34

 Downtown

0.33

 Chin

0.23

upt

0.23

 Kore

0.23

CBD

0.22

CWE

0.22

CBD

0.21

 trendy

0.20

 downt

0.18

Activations Density 0.387%

references to locations and establishments in New York City

No Comments

No Known Activations