INDEX

Explanations

descriptions of individuals and their professional roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

obel

-0.16

ehler

-0.15

ëį

-0.15

unge

-0.15

arser

-0.14

Ð°ÑĤÑĥ

-0.14

ingleton

-0.14

 Minerals

-0.14

ollar

-0.14

 ÎµÎ¼ÏĢ

-0.14

POSITIVE LOGITS

 born

0.29

 Born

0.29

Born

0.26

born

0.25

 native

0.25

 background

0.21

 natives

0.21

-born

0.20

 former

0.19

 Background

0.19

Activations Density 0.173%

descriptions of individuals and their professional roles

No Comments

No Known Activations

descriptions of individuals and their professional roles

No Comments

No Known Activations