INDEX

Explanations

locations and significant buildings or structures

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

 rencont

-0.16

amik

-0.15

ollision

-0.14

eea

-0.14

usat

-0.14

.IContainer

-0.14

mixed

-0.14

æŁľ

-0.14

ì¡±

-0.14

fÃ¼hr

-0.13

POSITIVE LOGITS

 estate

0.23

 house

0.20

 property

0.20

 mansion

0.20

estate

0.19

 Estate

0.18

 castle

0.18

 private

0.18

 family

0.17

 House

0.17

Activations Density 0.138%

locations and significant buildings or structures

No Comments

No Known Activations