INDEX

Explanations

phrases about research findings and their statistical significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

stringValue

-0.16

opis

-0.14

Ľ

-0.14

batim

-0.14

osa

-0.13

sko

-0.13

oma

-0.13

fuse

-0.13

afen

-0.13

 lekker

-0.13

POSITIVE LOGITS

 associations

0.32

 association

0.28

associ

0.26

 Associations

0.24

Associ

0.24

stat

0.22

 trends

0.22

 assoc

0.21

association

0.21

 direction

0.21

Activations Density 0.151%

phrases about research findings and their statistical significance

No Comments

No Known Activations