INDEX

Explanations

names and proper nouns related to people and places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ka

-0.30

li

-0.28

nya

-0.27

so

-0.24

la

-0.24

me

-0.23

ning

-0.23

ma

-0.23

ne

-0.23

che

-0.22

POSITIVE LOGITS

Ùĭ

0.26

ught

0.24

’nÄ±n

0.22

issance

0.22

ughter

0.21

'nÄ±n

0.21

election

0.20

irement

0.20

eus

0.20

ughty

0.19

Activations Density 1.018%

names and proper nouns related to people and places

No Comments

No Known Activations