INDEX

Explanations

statistical indicators and trends related to increases and decreases in data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

irsch

-0.15

isen

-0.15

Hao

-0.14

aux

-0.14

yes

-0.14

app

-0.14

embre

-0.14

 queryInterface

-0.13

 Stevenson

-0.13

avery

-0.13

POSITIVE LOGITS

eker

0.17

kou

0.15

á»įng

0.15

olas

0.15

benh

0.14

ILLISE

0.14

Editors

0.14

ctors

0.14

Kou

0.14

 Photon

0.14

Activations Density 0.112%

statistical indicators and trends related to increases and decreases in data

No Comments

No Known Activations