INDEX

Explanations

references to religious places and their significance

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

 Yemen

-0.17

 Hudson

-0.16

Î¯Î»

-0.15

apollo

-0.15

 Cairo

-0.14

ëįĺ

-0.14

HEN

-0.14

Qin

-0.14

Uy

-0.14

.Selection

-0.14

POSITIVE LOGITS

 Sikh

0.34

Sik

0.30

 Guru

0.30

 sangat

0.28

Pun

0.28

SG

0.27

 lang

0.27

Gur

0.25

à©

0.24

 à¨

0.24

Activations Density 0.069%

references to religious places and their significance

No Comments

No Known Activations