INDEX

Explanations

references to kinship or family relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

inos

-0.16

nell

-0.15

anyak

-0.15

insky

-0.14

zia

-0.14

å±±å¸Ĥ

-0.14

 famously

-0.14

vern

-0.14

odp

-0.14

 Ð¸Ð·Ð²ÐµÑģÑĤ

-0.14

POSITIVE LOGITS

Sin

0.15

or

0.14

tod

0.14

erg

0.14

emax

0.14

Ã¨n

0.13

dex

0.13

Ko

0.13

ref

0.13

,[

0.12

Activations Density 0.000%

references to kinship or family relationships

No Comments

No Known Activations