INDEX

Explanations

expressions of lack, absence, or deficiency in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

antro

-0.18

antar

-0.15

genic

-0.15

antan

-0.15

Tun

-0.14

poses

-0.14

çķ

-0.14

Ð½Ñİ

-0.14

ÏĢÎ¿

-0.14

 hopefully

-0.13

POSITIVE LOGITS

ÄĽ

0.17

/loose

0.15

éł¼

0.15

 fontStyle

0.14

ackers

0.14

 supervision

0.14

lan

0.14

 intertw

0.13

&,

0.13

adastro

0.13

Activations Density 0.181%

expressions of lack, absence, or deficiency in various contexts

No Comments

No Known Activations