INDEX

Explanations

abbreviations and acronyms frequently used in technical or organizational contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

å±

-0.16

CPF

-0.16

ions

-0.16

ocations

-0.15

ayet

-0.15

Ð¾Ð½Ð¾Ð²

-0.14

LayoutPanel

-0.14

kia

-0.13

him

-0.13

oll

-0.13

POSITIVE LOGITS

SGlobal

0.17

eda

0.16

oli

0.15

 Affero

0.15

allis

0.15

ollectors

0.14

adge

0.14

Ã©gorie

0.14

vecs

0.14

FTWARE

0.14

Activations Density 0.402%

abbreviations and acronyms frequently used in technical or organizational contexts

No Comments

No Known Activations