INDEX

Explanations

references to scientific publications and contributions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

stad

-0.17

 dressing

-0.15

orf

-0.15

etti

-0.15

ersh

-0.15

 Baby

-0.15

\OptionsResolver

-0.14

Ket

-0.14

enberg

-0.14

ìĦł

-0.14

POSITIVE LOGITS

 Natural

0.27

Natural

0.26

 natural

0.24

natural

0.21

tax

0.20

atural

0.20

zo

0.20

 museum

0.20

 Natur

0.20

 Challenger

0.20

Activations Density 0.132%

references to scientific publications and contributions

No Comments

No Known Activations