INDEX

Explanations

mentions of U.S. states and territories in a political or legal context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

kaÃ§

-0.15

avic

-0.14

Ø·

-0.14

asted

-0.14

 Nederland

-0.14

 Gauss

-0.14

SKTOP

-0.14

ITT

-0.13

çī

-0.13

POSITIVE LOGITS

 territories

0.48

 Territories

0.46

 Territory

0.40

 territory

0.40

territ

0.36

Terr

0.34

 Terr

0.32

 territorial

0.31

 territor

0.31

 possessions

0.27

Activations Density 0.085%

mentions of U.S. states and territories in a political or legal context

No Comments

No Known Activations