INDEX

Explanations

locations and experiences in a travel context

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

 discrepan

-0.17

ç´

-0.17

 summers

-0.16

pton

-0.16

haz

-0.16

 latina

-0.16

 vess

-0.15

Bea

-0.15

 Latina

-0.15

çº

-0.14

POSITIVE LOGITS

 Gecko

0.22

Hu

0.19

 local

0.18

 colonial

0.18

 chac

0.18

 Municip

0.18

 Quit

0.18

Gu

0.17

çĵľ

0.17

 volcano

0.17

Activations Density 0.069%

locations and experiences in a travel context

No Comments

No Known Activations