INDEX

Explanations

educational programs or initiatives aimed at facilitating learning and community engagement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

idth

-0.18

eger

-0.15

inear

-0.15

boom

-0.15

pend

-0.15

ilent

-0.14

ensible

-0.14

acus

-0.14

Äĩi

-0.14

 Beste

-0.14

POSITIVE LOGITS

ela

0.16

 Hass

0.14

explained

0.14

Ãºsqueda

0.14

 consists

0.14

 consisting

0.14

çĿ

0.14

isto

0.13

 concept

0.13

 Rich

0.13

Activations Density 0.228%

educational programs or initiatives aimed at facilitating learning and community engagement

No Comments

No Known Activations