INDEX

Explanations

proper nouns, specifically names of people and places

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 Pant

-0.14

 Millet

-0.14

quan

-0.14

Å¡etÅĻenÃŃ

-0.14

fade

-0.13

 Feinstein

-0.13

mlink

-0.13

 Astronomy

-0.13

 assist

-0.13

 Naomi

-0.12

POSITIVE LOGITS

atoria

0.15

TRL

0.15

alion

0.14

apel

0.14

ApiClient

0.14

Ð»Ñİ

0.14

imest

0.14

prov

0.14

locker

0.14

AccessException

0.13

Activations Density 0.996%

proper nouns, specifically names of people and places

No Comments

No Known Activations