INDEX

Explanations

phrases involving companionship or partnership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

edor

-0.15

ä½³

-0.15

yle

-0.15

ocht

-0.15

illin

-0.14

jac

-0.14

ymes

-0.14

htar

-0.14

èª¿

-0.14

POSITIVE LOGITS

nell

0.15

agher

0.14

 ÎłÎ»Î·

0.14

Gym

0.14

livÃ©

0.13

 Unit

0.13

Å¡t

0.13

ulator

0.13

Activations Density 0.011%

phrases involving companionship or partnership

No Comments

No Known Activations