INDEX

Explanations

phrases related to law and order, specifically in the context of authority and societal control

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

WWW

-0.16

rega

-0.15

 neoliberal

-0.14

æ§ĺ

-0.14

 Deng

-0.14

 politic

-0.14

regor

-0.14

Din

-0.13

snapshot

-0.13

zte

-0.13

POSITIVE LOGITS

RICS

0.14

ãĤ¨ãĥ«

0.13

=Math

0.13

.Generated

0.13

 semiclass

0.13

/frontend

0.13

ov

0.13

assin

0.13

unsupported

0.13

 Hemisphere

0.13

Activations Density 0.017%

phrases related to law and order, specifically in the context of authority and societal control

No Comments

No Known Activations