INDEX

Explanations

references to geographical locations and environmental features in Delhi

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

cen

-0.15

jiang

-0.15

/uploads

-0.14

 nors

-0.14

.Cascade

-0.14

Hoe

-0.14

 Maharashtra

-0.14

tright

-0.14

 armour

-0.14

 Bucc

-0.14

POSITIVE LOGITS

 Delhi

0.31

 Redskins

0.26

DC

0.25

DC

0.24

Washington

0.23

_DC

0.22

 Canberra

0.22

 Washington

0.22

 Capitals

0.21

 washington

0.21

Activations Density 0.200%

references to geographical locations and environmental features in Delhi

No Comments

No Known Activations