INDEX

Explanations

terms related to nucleotides and their structures in DNA

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 Shir

-0.17

 Sher

-0.15

pek

-0.14

Ã¡k

-0.14

 western

-0.14

opher

-0.14

-0.13

zone

-0.13

 ÐºÐ¾Ð²

-0.13

çĸ

-0.13

POSITIVE LOGITS

gu

0.27

 nucle

0.27

pur

0.26

Gu

0.24

din

0.23

AMP

0.23

enos

0.23

ad

0.23

gu

0.22

py

0.22

Activations Density 0.017%

terms related to nucleotides and their structures in DNA

No Comments

No Known Activations