INDEX

Explanations

terms related to computational simulations and energy potentials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

/send

-0.14

LOS

-0.14

zte

-0.14

velt

-0.13

åļ

-0.13

ãĥ¼ãĥł

-0.13

ÛĮØ±Ùĩ

-0.13

berg

-0.13

ÐµÐ´Ð¶

-0.13

antis

-0.12

POSITIVE LOGITS

Ìģt

0.16

osate

0.15

STANCE

0.15

Î¸Î¿

0.15

 Brewery

0.14

Łèĥ½

0.14

ASTER

0.14

 Buen

0.14

ç¢

0.13

Activations Density 0.017%

terms related to computational simulations and energy potentials

No Comments

No Known Activations