INDEX

Explanations

proper nouns, particularly names and titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

irÃ¡

-0.17

Ð±Ñĭ

-0.17

achat

-0.15

Î»Î¿Î¹

-0.15

urai

-0.15

 Rencontre

-0.14

Fur

-0.14

anut

-0.14

fur

-0.14

{name

-0.14

POSITIVE LOGITS

Tom

0.22

Tom

0.20

 Ð¢Ð¾Ð¼

0.17

ä»²

0.16

tom

0.16

å·±

0.15

é¡į

0.14

.rs

0.14

Aqu

0.14

ixo

0.14

Activations Density 0.029%

proper nouns, particularly names and titles

No Comments

No Known Activations