INDEX

Explanations

terms related to prevention and health issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 Ð²Ð¾ÑĢ

-0.15

ventus

-0.15

baum

-0.15

acific

-0.15

oningen

-0.14

aiser

-0.14

mbH

-0.14

udget

-0.14

esz

-0.14

à¤ł

-0.14

POSITIVE LOGITS

atively

0.23

/mit

0.23

ively

0.21

 further

0.20

ions

0.19

atives

0.19

ative

0.19

 Against

0.18

/manage

0.18

iable

0.18

Activations Density 0.027%

terms related to prevention and health issues

No Comments

No Known Activations