INDEX

Explanations

instances of rudeness and politeness in interactions

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

nock

-0.16

Ø²Ùĩ

-0.14

xing

-0.14

aver

-0.13

dag

-0.13

ãģ¥

-0.13

/live

-0.13

 puls

-0.13

dob

-0.13

enz

-0.13

POSITIVE LOGITS

Ã¤Ã¤

0.15

 Seznam

0.14

æµª

0.14

elu

0.14

ests

0.14

à¤ľà¤¨

0.14

à¸µà¹Ĥ

0.14

jen

0.14

sky

0.13

Activations Density 0.024%

instances of rudeness and politeness in interactions

No Comments

No Known Activations