INDEX

Explanations

references to specific geographic locations or cultural entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

oru

-0.17

 Rentals

-0.15

ä¼¼

-0.15

 rentals

-0.15

ë¦¬ìĸ´

-0.15

rer

-0.15

icot

-0.14

osaur

-0.14

 Rossi

-0.14

 ])->

-0.14

POSITIVE LOGITS

ÑĢÑĥÐ¶

0.17

edo

0.16

 loadData

0.15

Ð¾Ð¼ÐµÑĢ

0.14

stone

0.14

aved

0.14

wik

0.14

adera

0.14

bon

0.14

Ð´ÑĢÐµÑģ

0.14

Activations Density 0.024%

references to specific geographic locations or cultural entities

No Comments

No Known Activations