INDEX

Explanations

instances of persuasion or convincing in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

gie

-0.17

olen

-0.15

igest

-0.14

fÃ¼

-0.14

ICI

-0.14

iese

-0.14

DMI

-0.14

yms

-0.14

ifice

-0.13

POSITIVE LOGITS

 convin

0.24

 convinced

0.22

 convince

0.22

 Conv

0.21

ively

0.20

conv

0.20

 persu

0.19

 convincing

0.19

Conv

0.18

 persuade

0.18

Activations Density 0.021%

instances of persuasion or convincing in various contexts

No Comments

No Known Activations