INDEX

Explanations

references to social interactions in cafés and parks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ulton

-0.18

 dinner

-0.17

 Dinner

-0.16

Cook

-0.16

 cooking

-0.16

 Cooking

-0.16

 shower

-0.15

ledge

-0.15

 cook

-0.15

POSITIVE LOGITS

 coffee

0.23

 caffe

0.23

 cafe

0.22

Coffee

0.21

 Starbucks

0.21

 cafÃ©

0.21

 Coffee

0.20

 caffeine

0.19

 coff

0.19

ì»

0.18

Activations Density 0.099%

references to social interactions in cafés and parks

No Comments

No Known Activations