INDEX

Explanations

quantities and measurements related to various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

isoft

-0.17

mil

-0.15

åĮ

-0.15

à¥ĩà¤¦

-0.15

STER

-0.14

efa

-0.14

elastic

-0.14

Ø§Ø²ÛĮ

-0.14

è¿ĺæĺ¯

-0.13

.rabbit

-0.13

POSITIVE LOGITS

 depending

0.27

depending

0.21

 alike

0.18

grounds

0.15

 respectively

0.15

acent

0.15

 dependent

0.15

 Depending

0.15

Eg

0.15

 Tamb

0.15

Activations Density 0.043%

quantities and measurements related to various subjects

No Comments

No Known Activations