INDEX

Explanations

references to biological or genetic concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

-0.14

amus

-0.14

ãĥ³ãĥĪ

-0.14

umann

-0.14

ajan

-0.13

ummer

-0.13

Ð½Ð¸ÑĨ

-0.13

afia

-0.13

 datum

-0.13

POSITIVE LOGITS

 membr

0.22

 Stick

0.22

 Protein

0.21

 mole

0.21

 Prote

0.20

 Cycl

0.19

Ox

0.19

 struk

0.18

 Hydro

0.18

 stick

0.18

Activations Density 0.008%

references to biological or genetic concepts

No Comments

No Known Activations