INDEX

Explanations

instances of the word "app" and related forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

Ã¤ge

-0.20

adera

-0.18

eping

-0.18

ep

-0.15

cker

-0.15

esters

-0.15

idelity

-0.15

esti

-0.15

ctor

-0.14

etter

-0.14

POSITIVE LOGITS

alach

0.26

licable

0.26

rais

0.25

ropriate

0.24

lic

0.23

raised

0.23

ellation

0.23

ointed

0.22

ended

0.22

arent

0.21

Activations Density 0.017%

instances of the word "app" and related forms

No Comments

No Known Activations