INDEX

Explanations

references to predators and prey interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

aths

-0.14

 pornografia

-0.14

-commercial

-0.14

 prostitu

-0.14

ampo

-0.13

Atl

-0.13

 dwar

-0.13

ÌĨ

-0.13

/UIKit

-0.13

amine

-0.13

POSITIVE LOGITS

 predators

0.28

 pred

0.26

 predator

0.24

 predatory

0.23

Pred

0.22

 prey

0.22

 Predator

0.21

 Pred

0.20

pred

0.19

 attacks

0.19

Activations Density 0.083%

references to predators and prey interactions

No Comments

No Known Activations