INDEX

Explanations

questions and affirmative statements

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

↵

-0.42

↵

-0.25

Âł↵

-0.21

à¥ĩ↵

-0.19

à¸µ↵

-0.18

à¤¾↵

-0.17

<|end_of_text|>

-0.17

à¥Ģ↵

-0.17

↵↵

-0.17

à¸µà¹ī↵

-0.17

POSITIVE LOGITS

odore

0.33

 Their

0.26

adays

0.24

 Your

0.22

atre

0.22

You

0.21

You

0.21

 Yourself

0.20

Your

0.20

 These

0.19

Activations Density 0.564%

questions and affirmative statements

No Comments

No Known Activations