INDEX

Explanations

phrases indicating academic research or citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

urn

-0.15

 Levine

-0.15

ayer

-0.15

arel

-0.14

Dy

-0.14

 serialVersionUID

-0.14

central

-0.14

Sym

-0.14

 central

-0.13

Fin

-0.13

POSITIVE LOGITS

enson

0.17

>NN

0.16

enderror

0.16

Ã¡bado

0.15

.epam

0.15

afia

0.15

eniz

0.15

Ã¹i

0.14

itzer

0.14

 feeder

0.14

Activations Density 0.003%

phrases indicating academic research or citations

No Comments

No Known Activations