INDEX

Explanations

concepts related to political hypocrisy and criticism

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ektor

-0.15

Province

-0.14

ÐµÐ³Ð°

-0.14

 ká»·

-0.13

 dziew

-0.13

Paren

-0.12

ansen

-0.12

aris

-0.12

Î±Î½Î´

-0.12

 Photon

-0.12

POSITIVE LOGITS

 political

1.00

 politics

0.91

 Political

0.85

political

0.80

 Politics

0.74

æĶ¿æ²»

0.73

 polit

0.71

 polÃŃtica

0.70

 Ð¿Ð¾Ð»Ð¸ÑĤ

0.69

Political

0.69

Activations Density 0.898%

concepts related to political hypocrisy and criticism

No Comments

No Known Activations