INDEX

Explanations

references to specific geographic locations and communities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

sou

-0.20

åįĹ

-0.19

sou

-0.19

Southern

-0.19

 Southern

-0.19

South

-0.19

 Southwest

-0.18

ffen

-0.17

south

-0.17

 South

-0.17

POSITIVE LOGITS

 Northern

0.39

Northern

0.36

 northern

0.36

 North

0.34

 north

0.32

 Northwestern

0.31

åĮĹ

0.31

 NORTH

0.30

North

0.30

 åĮĹ

0.29

Activations Density 0.197%

references to specific geographic locations and communities

No Comments

No Known Activations