INDEX

Explanations

expressions indicating requirements and actions in the context of healthcare and legal procedures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

undry

-0.18

unto

-0.15

ieg

-0.15

ure

-0.15

allery

-0.14

inn

-0.14

loo

-0.14

Storm

-0.14

ole

-0.14

unt

-0.14

POSITIVE LOGITS

ieux

0.17

estone

0.16

idores

0.15

 Spotlight

0.15

_INCLUDED

0.14

 categorical

0.14

 Sind

0.14

igaret

0.14

lid

0.13

é¡Ķ

0.13

Activations Density 0.116%

expressions indicating requirements and actions in the context of healthcare and legal procedures

No Comments

No Known Activations