INDEX

Explanations

phrases indicating uncertainty or negation regarding existence or quality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

aper

-0.17

etch

-0.16

leo

-0.16

 nackte

-0.15

ouv

-0.15

avn

-0.14

 McCabe

-0.14

á»ģn

-0.13

variants

-0.13

 Stateless

-0.13

POSITIVE LOGITS

 chances

0.28

 need

0.27

 possibility

0.26

 chance

0.23

 probability

0.21

 likelihood

0.20

need

0.19

 Need

0.19

 possibilities

0.19

 Probability

0.18

Activations Density 0.064%

phrases indicating uncertainty or negation regarding existence or quality

No Comments

No Known Activations