INDEX

Explanations

geographic locations and demographic descriptors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 Economy

-0.16

osi

-0.15

 Budget

-0.15

 budget

-0.15

acr

-0.15

 Globe

-0.15

weise

-0.15

 Gallup

-0.15

 Industrial

-0.14

 warehouse

-0.14

POSITIVE LOGITS

exclusive

0.24

 exclusive

0.24

 Beverly

0.23

 polo

0.22

 exclus

0.20

 Tennis

0.20

-exclusive

0.20

 Exclusive

0.20

pos

0.19

 tennis

0.19

Activations Density 0.310%

geographic locations and demographic descriptors

No Comments

No Known Activations