INDEX

Explanations

references to countries and international organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

atik

-0.16

acon

-0.15

lington

-0.14

inand

-0.14

olumn

-0.14

erton

-0.13

Tot

-0.13

rie

-0.13

Tot

-0.13

aber

-0.13

POSITIVE LOGITS

ÐµÐ»ÐµÐ½

0.20

aille

0.15

uez

0.15

ixe

0.15

etiyle

0.15

hlen

0.14

 Invoke

0.14

eca

0.14

Ø±Ùĥ

0.14

ailles

0.14

Activations Density 0.016%

references to countries and international organizations

No Comments

No Known Activations