INDEX

Explanations

references to advertisements, particularly those related to matrimonial services and classified ads

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

æ£ļ

-0.15

ileo

-0.14

isposable

-0.14

hangi

-0.14

ulary

-0.14

.Library

-0.13

imeo

-0.13

 Moody

-0.13

oteca

-0.13

ulture

-0.13

POSITIVE LOGITS

 Classified

0.52

 classified

0.51

classified

0.45

ads

0.41

 listings

0.36

Ads

0.36

 listing

0.34

Ads

0.33

 Craigslist

0.32

 Craig

0.30

Activations Density 0.159%

references to advertisements, particularly those related to matrimonial services and classified ads

No Comments

No Known Activations