INDEX

Explanations

references to government actions and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

fak

-0.16

pez

-0.14

apat

-0.14

SEN

-0.13

oin

-0.13

Î´Î¹Îº

-0.13

 ØŃÙĤÙĪÙĤ

-0.13

elin

-0.13

qui

-0.13

enza

-0.13

POSITIVE LOGITS

 government

0.95

government

0.80

 Government

0.80

æĶ¿åºľ

0.74

Government

0.71

 governments

0.65

-government

0.64

 governo

0.62

 gobierno

0.59

 à¤¸à¤°à¤ķ

0.56

Activations Density 0.332%

references to government actions and structures

No Comments

No Known Activations