INDEX

Explanations

specific numerical values and phrases indicating significant concepts or positive attributes

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

ALSE

-0.17

erville

-0.16

aho

-0.15

Ĩ

-0.15

 multis

-0.14

ë¨¹

-0.14

ãģķãĤī

-0.14

isse

-0.14

cause

-0.14

ibo

-0.14

POSITIVE LOGITS

leigh

0.16

 Mond

0.15

anged

0.15

 Termin

0.14

 Hayden

0.14

oll

0.14

Î¸Î¼

0.14

 Orta

0.14

arry

0.14

 acronym

0.14

Activations Density 0.003%

specific numerical values and phrases indicating significant concepts or positive attributes

No Comments

No Known Activations