INDEX

Explanations

instructions or teachings directed towards others, particularly regarding learning and personal development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

omo

-0.21

omor

-0.15

marks

-0.15

otte

-0.14

atÃ³

-0.14

_Info

-0.14

urat

-0.14

ilha

-0.14

olan

-0.14

.LoggerFactory

-0.13

POSITIVE LOGITS

ardown

0.16

EMON

0.15

 caul

0.15

baum

0.14

 Touch

0.14

oda

0.14

ppe

0.14

á»©ng

0.13

ByVersion

0.13

izard

0.13

Activations Density 0.028%

instructions or teachings directed towards others, particularly regarding learning and personal development

No Comments

No Known Activations