INDEX

Explanations

instances of places and geographical locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

quo

-0.18

Ã¤tz

-0.15

occ

-0.15

meld

-0.14

oca

-0.14

ployment

-0.14

olvable

-0.14

seau

-0.14

quets

-0.14

inae

-0.14

POSITIVE LOGITS

 visit

0.35

 trip

0.32

 visits

0.30

visit

0.29

 visited

0.28

 visiting

0.28

_visit

0.27

 visita

0.27

 Visit

0.26

 tour

0.25

Activations Density 0.099%

instances of places and geographical locations

No Comments

No Known Activations