INDEX

Explanations

terms related to cinematic or artistic representations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

jezd

-0.15

.BLL

-0.15

romo

-0.15

ibi

-0.14

 Burke

-0.14

 Learned

-0.14

¢°

-0.13

Eld

-0.13

/link

-0.13

 Loft

-0.13

POSITIVE LOGITS

 à¤ķà¤¡

0.20

 hyper

0.18

-L

0.17

 Hyper

0.17

hyp

0.17

 liÃªn

0.16

-l

0.16

à¸¥

0.15

 Scar

0.15

 tink

0.15

Activations Density 0.009%

terms related to cinematic or artistic representations

No Comments

No Known Activations