INDEX

Explanations

references to organizational or project missions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

porter

-0.17

reau

-0.16

ÃŃa

-0.15

Arena

-0.15

idence

-0.15

sak

-0.14

utow

-0.14

 Shelf

-0.14

 Arena

-0.14

ventions

-0.14

POSITIVE LOGITS

aries

0.40

ary

0.34

 statement

0.30

naire

0.27

 critical

0.27

 Critical

0.26

naires

0.26

 Statement

0.25

critical

0.25

 accomplished

0.25

Activations Density 0.019%

references to organizational or project missions

No Comments

No Known Activations