INDEX

Explanations

phrases related to various types of locations and settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

åľĴ

-0.15

zem

-0.15

ÐµÐ»ÐµÑĦ

-0.15

 accommod

-0.14

Kitchen

-0.14

âĢĮØ¯Ùĩ

-0.14

fts

-0.14

ctr

-0.14

 trainable

-0.14

 balcon

-0.13

POSITIVE LOGITS

 remote

0.24

 unnamed

0.21

 undisclosed

0.20

 deserted

0.19

remote

0.18

 resort

0.18

 private

0.17

 local

0.17

.remote

0.17

 nearby

0.16

Activations Density 0.383%

phrases related to various types of locations and settings

No Comments

No Known Activations