INDEX

Explanations

key figures and names in discussions about cultural or social critiques

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

-vous

-0.17

atically

-0.16

forth

-0.16

ÙĦØ·

-0.15

ably

-0.15

empre

-0.15

aurus

-0.15

zelf

-0.15

bove

-0.15

ourse

-0.14

POSITIVE LOGITS

most

0.24

bies

0.22

-fashioned

0.22

-ÑĤÐ°ÐºÐ¸

0.21

er

0.21

edException

0.19

 Ø¨ÙĪØ§Ø¨Ø©

0.19

à¹Ĩ

0.18

coming

0.18

ish

0.18

Activations Density 0.279%

key figures and names in discussions about cultural or social critiques

No Comments

No Known Activations