INDEX

Explanations

phrases that suggest reactions or emotional responses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ipel

-0.15

ï½ľ

-0.14

 (“

-0.14

adi

-0.14

ome

-0.14

asin

-0.13

te

-0.13

æĽ¾

-0.13

 neighb

-0.13

castle

-0.13

POSITIVE LOGITS

zia

0.17

0.16

ALAR

0.15

venta

0.14

fy

0.14

aroo

0.14

endas

0.13

itou

0.13

 gest

0.13

anzi

0.13

Activations Density 0.018%

phrases that suggest reactions or emotional responses

No Comments

No Known Activations