INDEX

Explanations

terms related to heating and fireplace systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

vale

-0.16

 Humb

-0.16

LEC

-0.15

lec

-0.15

Ã³b

-0.14

 sensitive

-0.14

ursed

-0.14

 alien

-0.13

 Eagle

-0.13

 nerve

-0.13

POSITIVE LOGITS

 fireplace

0.29

 Fireplace

0.27

 Hearth

0.23

 fuels

0.23

 Logs

0.21

 logs

0.20

 ashes

0.20

bri

0.20

 chimney

0.20

 stove

0.19

Activations Density 0.067%

terms related to heating and fireplace systems

No Comments

No Known Activations