INDEX

Explanations

details about a specific location or place

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

 CITY

-0.18

stad

-0.17

 City

-0.17

 city

-0.17

 metro

-0.16

 cities

-0.16

VERIFY

-0.16

 Metro

-0.16

 Cities

-0.15

metro

-0.15

POSITIVE LOGITS

 village

0.35

 Village

0.28

 villagers

0.27

æĿĳ

0.27

illage

0.21

 church

0.21

 parish

0.20

 Rural

0.20

 rural

0.20

 Parish

0.20

Activations Density 0.221%

details about a specific location or place

No Comments

No Known Activations