INDEX

Explanations

instances of the word "ad" 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 @ 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

-0.37

er

-0.34

iÄĩ

-0.30

eria

-0.29

ar

-0.28

-0.27

iya

-0.27

iw

-0.26

aat

-0.26

POSITIVE LOGITS

venture

0.20

vertising

0.19

vice

0.16

vertiser

0.16

option

0.16

ec

0.16

dd

0.16

ad

0.15

emy

0.15

eg

0.15

Activations Density 0.023%

instances of the word "ad" in various contexts

No Comments

No Known Activations