INDEX

Explanations

terms related to guidance and assistance in a digital context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

lip

-0.16

Lip

-0.15

veau

-0.15

 instrument

-0.14

 signature

-0.14

oria

-0.14

 head

-0.14

lich

-0.14

Ä°Åŀ

-0.13

igon

-0.13

POSITIVE LOGITS

abeth

0.18

linky

0.16

ago

0.15

 PROGMEM

0.15

 pollen

0.15

 Hall

0.15

elight

0.15

Hall

0.14

opi

0.14

cih

0.14

Activations Density 0.001%

terms related to guidance and assistance in a digital context

No Comments

No Known Activations