INDEX

Explanations

proper nouns and names related to individuals and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

elf

-0.18

DEM

-0.17

ibar

-0.16

presso

-0.15

reen

-0.15

-0.14

æ»ħ

-0.14

angu

-0.14

Ð²Ð¾Ñİ

-0.14

resse

-0.14

POSITIVE LOGITS

ounced

0.17

iples

0.16

Äħd

0.15

apore

0.15

eworthy

0.15

ordial

0.15

Cog

0.14

folio

0.14

rzy

0.14

iminary

0.14

Activations Density 0.022%

proper nouns and names related to individuals and organizations

No Comments

No Known Activations