INDEX

Explanations

references to "America" and its related terms

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

manship

-0.17

il

-0.15

Ú¯Ø§Ùĩ

-0.15

immer

-0.15

ëģĶ

-0.15

ilate

-0.15

istrovstvÃŃ

-0.14

quee

-0.14

Ð¿Ð¸Ñģ

-0.14

POSITIVE LOGITS

 Samoa

0.26

 BirleÅŁik

0.22

ized

0.21

 Idol

0.18

 Latina

0.18

arily

0.18

adol

0.18

 continents

0.17

ised

0.17

 continent

0.17

Activations Density 0.059%

references to "America" and its related terms

No Comments

No Known Activations

references to "America" and its related terms

No Comments

No Known Activations