INDEX

Explanations

expressions of gratitude and positivity, particularly in relation to experiences and accomplishments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

otomy

-0.14

avir

-0.14

weeney

-0.14

ahrung

-0.14

ubar

-0.14

owie

-0.14

 tent

-0.14

 undef

-0.13

ioc

-0.13

eki

-0.13

POSITIVE LOGITS

 possibly

0.30

ask

0.29

 asks

0.27

ask

0.26

 asked

0.25

Ask

0.24

 Possibly

0.24

 dream

0.23

 asking

0.22

 possible

0.22

Activations Density 0.024%

expressions of gratitude and positivity, particularly in relation to experiences and accomplishments

No Comments

No Known Activations