INDEX

Explanations

mentions of the term "net" and related financial metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

á»©ng

-0.17

nerg

-0.17

apers

-0.16

onest

-0.16

.googleapis

-0.16

inated

-0.16

hit

-0.15

aper

-0.15

naire

-0.14

POSITIVE LOGITS

tle

0.33

lify

0.33

izens

0.30

ted

0.28

flix

0.27

ting

0.26

izen

0.26

ters

0.26

CDF

0.25

Ø§Ø¦Ø¬

0.25

Activations Density 0.026%

mentions of the term "net" and related financial metrics

No Comments

No Known Activations