INDEX

Explanations

locations and addresses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

icho

-0.20

ordes

-0.16

aldi

-0.16

evin

-0.15

ayan

-0.14

raki

-0.14

antium

-0.14

 KrÃ¡l

-0.14

 ä½Ĳ

-0.14

-UA

-0.13

POSITIVE LOGITS

 Olsen

0.17

 Wagner

0.15

ung

0.14

 Cemetery

0.14

ä¹Ļ

0.14

 County

0.13

 Main

0.13

 Compound

0.13

.pose

0.13

 Arist

0.13

Activations Density 0.081%

locations and addresses

No Comments

No Known Activations