INDEX

Explanations

expressions related to accessibility and universality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

others

-0.15

UTE

-0.15

ute

-0.15

 Others

-0.14

elog

-0.14

lÃ½

-0.14

Others

-0.13

aska

-0.13

 others

-0.13

aldi

-0.13

POSITIVE LOGITS

 everywhere

0.27

 anywhere

0.24

 anytime

0.22

 anything

0.21

Anywhere

0.20

 every

0.20

 nowhere

0.20

 everything

0.19

any

0.18

every

0.18

Activations Density 0.096%

expressions related to accessibility and universality

No Comments

No Known Activations