INDEX

Explanations

references to research studies or scholarly articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

icont

-0.16

arin

-0.14

oning

-0.14

MAND

-0.14

bine

-0.14

iale

-0.14

XObject

-0.14

ÏĥÎ¿Ïħ

-0.14

olang

-0.14

.ObjectModel

-0.14

POSITIVE LOGITS

 Polit

0.15

inae

0.14

ÙĪÙĤ

0.14

usch

0.14

kop

0.14

 Retirement

0.14

Sof

0.13

 Software

0.13

 extent

0.13

Activations Density 0.152%

references to research studies or scholarly articles

No Comments

No Known Activations