INDEX

Explanations

references to neutron stars and associated theoretical frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

EMS

-0.17

PRETTY

-0.17

lcm

-0.15

KHTML

-0.15

Î¿Îº

-0.15

å°Ĭ

-0.15

Ð°Ð´ÐºÐ¸

-0.15

isOk

-0.15

rane

-0.14

enas

-0.14

POSITIVE LOGITS

 Nuclear

0.18

 nuclear

0.18

otland

0.15

hic

0.15

pile

0.15

sea

0.14

babel

0.14

 Trit

0.14

 Underground

0.14

 solar

0.14

Activations Density 0.001%

references to neutron stars and associated theoretical frameworks

No Comments

No Known Activations