INDEX

Explanations

mentions of geographic locations and entities related to community events

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

ponge

-0.15

raison

-0.15

CHIP

-0.15

-0.14

eva

-0.14

 Mund

-0.14

inct

-0.14

 plage

-0.14

BarController

-0.14

POSITIVE LOGITS

 Winston

0.27

 Greens

0.26

 Fors

0.25

 Clem

0.25

Yad

0.25

 Ashe

0.24

 Alam

0.23

 Guil

0.23

 Kern

0.23

 Elon

0.20

Activations Density 0.020%

mentions of geographic locations and entities related to community events

No Comments

No Known Activations