INDEX

Explanations

mentions of universities and educational institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

irt

-0.18

bsp

-0.17

ory

-0.16

uzzi

-0.16

iani

-0.15

fce

-0.14

fx

-0.14

akah

-0.14

oci

-0.14

loha

-0.14

POSITIVE LOGITS

 Notre

0.23

 British

0.22

 California

0.21

 Southern

0.20

 Texas

0.20

 Illinois

0.20

 Arizona

0.20

 Maryland

0.19

 Minnesota

0.19

 Wisconsin

0.19

Activations Density 0.015%

mentions of universities and educational institutions

No Comments

No Known Activations