INDEX

Explanations

references to community organizations and associated individuals

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

otos

-0.17

 saturn

-0.15

åī²

-0.15

adium

-0.15

æŀľ

-0.14

igos

-0.14

Ð¿ÑĢÐ¸Ð¼ÐµÑĢ

-0.14

.writeValue

-0.14

ffee

-0.14

ëŀ

-0.14

POSITIVE LOGITS

 Sussex

0.36

 Brighton

0.36

Sus

0.29

Bright

0.29

Lew

0.29

sus

0.28

 Hastings

0.25

Wor

0.23

Fal

0.23

SUS

0.22

Activations Density 0.011%

references to community organizations and associated individuals

No Comments

No Known Activations