INDEX

Explanations

elements related to surveillance and censorship

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ilig

-0.16

 chung

-0.15

jist

-0.15

UNUSED

-0.14

Ã¼gen

-0.14

é¨

-0.14

rix

-0.14

NCY

-0.14

VML

-0.13

igmoid

-0.13

POSITIVE LOGITS

 dissent

0.32

 challenge

0.29

 critical

0.27

 daring

0.26

 dared

0.26

 perceived

0.26

 challenging

0.26

æķ¢

0.25

 critic

0.25

 slightest

0.25

Activations Density 0.379%

elements related to surveillance and censorship

No Comments

No Known Activations