INDEX

Explanations

phrases that indicate insights, revelations, or the sharing of knowledge and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

enk

-0.16

avern

-0.15

isha

-0.15

pch

-0.15

 interiors

-0.15

otu

-0.14

cord

-0.14

anz

-0.14

xon

-0.14

avig

-0.14

POSITIVE LOGITS

 lessons

0.32

 lesson

0.31

 insights

0.29

 Lesson

0.29

 insight

0.28

Lesson

0.27

lessons

0.26

 learn

0.26

 Lessons

0.26

lesson

0.26

Activations Density 0.018%

phrases that indicate insights, revelations, or the sharing of knowledge and experiences

No Comments

No Known Activations