INDEX

Explanations

announcements and recognitions within a professional context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

hower

-0.16

auer

-0.15

abez

-0.14

udeau

-0.14

bove

-0.14

%%↵

-0.14

jedn

-0.13

_then

-0.13

ë¹Ļ

-0.13

oire

-0.13

POSITIVE LOGITS

wi

0.15

omik

0.15

oru

0.15

uku

0.14

 today

0.14

achsen

0.14

ishi

0.14

0.13

 incons

0.13

ome

0.13

Activations Density 0.402%

announcements and recognitions within a professional context

No Comments

No Known Activations