INDEX

Explanations

references to the word "you" emphasizing personal engagement and address

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

asic

-0.17

 Fleming

-0.16

adio

-0.15

ADIO

-0.14

leg

-0.14

ej

-0.13

Ð¸Ð¼Ð°Ð»ÑĮ

-0.13

loff

-0.13

Fu

-0.13

 Sesso

-0.13

POSITIVE LOGITS

bjerg

0.16

à¥Ŀ

0.15

odoxy

0.15

ivery

0.15

DoubleClick

0.15

å¤®

0.15

 unserialize

0.14

erer

0.14

æģ©

0.14

umlu

0.14

Activations Density 0.019%

references to the word "you" emphasizing personal engagement and address

No Comments

No Known Activations