INDEX

Explanations

references to geographic locations and local communities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

sou

-0.20

Southern

-0.20

 Southern

-0.19

åįĹ

-0.19

South

-0.19

 southern

-0.18

south

-0.18

å¢¨

-0.17

 Southwest

-0.17

POSITIVE LOGITS

 Northern

0.37

 northern

0.35

 North

0.34

Northern

0.33

 north

0.31

 Northwestern

0.30

åĮĹ

0.30

 NORTH

0.30

North

0.29

 nord

0.28

Activations Density 0.204%

references to geographic locations and local communities

No Comments

No Known Activations