INDEX

Explanations

financial and efficiency-related terms concerning energy usage and costs

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

eba

-0.15

etti

-0.14

ÎŃÏĤ

-0.14

ewire

-0.14

oÅ¾

-0.13

ãĥ¼ãĥĬ

-0.13

ç¾¤

-0.13

 stocking

-0.13

 rend

-0.13

vfs

-0.13

POSITIVE LOGITS

 bills

0.28

 bill

0.24

phia

0.22

.bill

0.20

 Bills

0.19

 Usage

0.17

 monthly

0.17

 usage

0.16

lick

0.16

_bill

0.16

Activations Density 0.043%

financial and efficiency-related terms concerning energy usage and costs

No Comments

No Known Activations