INDEX

Explanations

references to various art exhibitions and related events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 Zaman

-0.15

ovich

-0.15

usk

-0.15

 Becker

-0.14

rada

-0.14

 Clement

-0.14

addle

-0.14

oland

-0.14

Ú©Ø§Ø±ÛĮ

-0.14

visor

-0.13

POSITIVE LOGITS

Lod

0.20

 Split

0.19

 Nancy

0.18

 lille

0.18

 Gent

0.17

Vil

0.17

Deb

0.17

 Tours

0.17

 Latina

0.17

 Tall

0.17

Activations Density 0.281%

references to various art exhibitions and related events

No Comments

No Known Activations