INDEX

Explanations

proper nouns related to specific geographic locations and institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

eson

-0.17

raÅ¾

-0.16

ito

-0.16

omas

-0.15

 Creek

-0.15

ehir

-0.15

ģm

-0.14

agher

-0.14

ulkan

-0.14

amina

-0.14

POSITIVE LOGITS

 region

0.35

region

0.30

-region

0.29

 area

0.28

-area

0.27

 Region

0.26

area

0.24

 Area

0.21

Region

0.21

-wide

0.19

Activations Density 0.096%

proper nouns related to specific geographic locations and institutions

No Comments

No Known Activations