INDEX

Explanations

mention of specific locations and experiences related to dining and food

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 resorts

-0.18

 hospitals

-0.17

 hotels

-0.16

 companies

-0.16

 schools

-0.16

 Companies

-0.16

Companies

-0.16

 airports

-0.15

_CAST

-0.15

 Hotels

-0.14

POSITIVE LOGITS

 Frequ

0.24

 owned

0.21

 frequ

0.20

owner

0.19

 opened

0.19

 serving

0.19

 owner

0.19

 located

0.18

 atmosphere

0.18

 Serving

0.18

Activations Density 0.139%

mention of specific locations and experiences related to dining and food

No Comments

No Known Activations