INDEX

Explanations

references to religious institutions and figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

rana

-0.15

HLT

-0.15

eah

-0.15

veau

-0.15

 genome

-0.14

íĨµ

-0.14

poz

-0.14

asje

-0.14

Ø´ÛĮ

-0.14

afil

-0.14

POSITIVE LOGITS

 Parish

0.29

 Roman

0.27

 Catholic

0.27

RC

0.26

 parish

0.26

 Basil

0.24

 Cathedral

0.24

-on

0.24

-in

0.23

inus

0.22

Activations Density 0.030%

references to religious institutions and figures

No Comments

No Known Activations