INDEX

Explanations

punctuation marks, particularly parentheses, indicating additional information or clarifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

positor

-0.18

jian

-0.17

wizard

-0.17

esor

-0.15

Ã¡du

-0.15

aliz

-0.15

 ÑģÐ¸Ð»Ñĥ

-0.15

etros

-0.15

iyon

-0.15

 voksne

-0.15

POSITIVE LOGITS

 both

0.19

both

0.16

etc

0.16

 Pale

0.15

 conv

0.15

 latter

0.15

ford

0.15

ollo

0.14

ro

0.14

osphere

0.14

Activations Density 0.180%

punctuation marks, particularly parentheses, indicating additional information or clarifications

No Comments

No Known Activations