INDEX

Explanations

place names and geographic 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

States

-0.17

 Saunders

-0.15

.states

-0.14

 STATES

-0.14

AGER

-0.13

_states

-0.13

utex

-0.13

ocracy

-0.13

astic

-0.13

arium

-0.13

POSITIVE LOGITS

-area

0.31

 city

0.31

å¸Ĥ

0.26

shire

0.24

 City

0.24

-based

0.23

city

0.23

 area

0.22

 Mayor

0.21

-city

0.21

Activations Density 0.639%

place names and geographic locations

No Comments

No Known Activations