INDEX

Explanations

measurements related to depth and height

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

nez

-0.15

Lob

-0.15

Ð¸Ð½ÐºÑĥ

-0.15

gnore

-0.15

hti

-0.14

 longitud

-0.14

ÑĤÑİ

-0.14

arg

-0.14

tring

-0.14

otherapy

-0.14

POSITIVE LOGITS

 depth

0.23

 depths

0.21

-depth

0.19

 layer

0.19

 layers

0.18

 height

0.18

depth

0.18

-height

0.17

 heights

0.17

 Depth

0.17

Activations Density 0.116%

measurements related to depth and height

No Comments

No Known Activations