INDEX

Explanations

mentions of stock market indices, particularly associated with the NASDAQ

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 erect

-0.18

enk

-0.15

elts

-0.15

ayar

-0.14

isch

-0.14

egers

-0.14

swire

-0.14

etting

-0.14

à¹Ĥà¸¡

-0.14

owie

-0.14

POSITIVE LOGITS

daq

0.32

DAQ

0.29

cent

0.21

areth

0.20

ucas

0.19

Ä±l

0.18

heed

0.18

quer

0.17

CENT

0.16

ional

0.16

Activations Density 0.010%

mentions of stock market indices, particularly associated with the NASDAQ

No Comments

No Known Activations