INDEX

Explanations

references to locations and movements between places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

anes

-0.17

auer

-0.15

ead

-0.14

Ø§ÙĨÙĬØ§

-0.14

ad

-0.14

lamaz

-0.14

CADE

-0.14

agate

-0.13

%B

-0.13

jang

-0.13

POSITIVE LOGITS

 elsewhere

0.32

 overseas

0.21

Else

0.20

 abroad

0.19

 Else

0.19

NewItem

0.18

 FOREIGN

0.18

 foreign

0.17

 altre

0.17

 Morrow

0.17

Activations Density 0.217%

references to locations and movements between places

No Comments

No Known Activations