INDEX

Explanations

proper nouns related to locations and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

elles

-0.16

 Asheville

-0.15

raig

-0.15

hip

-0.15

 Orlando

-0.14

stag

-0.14

 mountain

-0.14

éłĺ

-0.13

.ie

-0.13

orida

-0.13

POSITIVE LOGITS

 Lincoln

0.30

 Hull

0.29

 Omaha

0.28

 Nebraska

0.27

 york

0.20

York

0.20

Lin

0.19

 Yorkshire

0.18

 Sunderland

0.18

 York

0.18

Activations Density 0.020%

proper nouns related to locations and organizations

No Comments

No Known Activations