INDEX

Explanations

instances of teaching, learning, and guidance in various contexts

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

 Yourself

-0.20

 yourself

-0.19

 oneself

-0.17

 ourselves

-0.17

 yourselves

-0.17

_RESOURCES

-0.16

-your

-0.16

au

-0.14

RectTransform

-0.14

ai

-0.14

POSITIVE LOGITS

us

0.31

me

0.30

him

0.19

 them

0.18

 Ð¼Ð½Ðµ

0.18

chyb

0.17

æĪĳ

0.15

you

0.15

utzer

0.15

UnitTest

0.15

Activations Density 0.322%

instances of teaching, learning, and guidance in various contexts

No Comments

No Known Activations