INDEX

Explanations

names of people and entities, particularly focusing on specific individuals and their relationships or backgrounds

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

INGTON

-0.15

eteria

-0.15

atsapp

-0.15

tember

-0.15

ickers

-0.15

ãĥĬãĥ¼

-0.15

licants

-0.15

atoria

-0.14

ilight

-0.14

alten

-0.14

POSITIVE LOGITS

Jr

0.34

-Smith

0.31

of

0.25

PhD

0.25

/AFP

0.24

akis

0.24

-B

0.24

0.23

/Getty

0.23

-W

0.23

Activations Density 0.169%

names of people and entities, particularly focusing on specific individuals and their relationships or backgrounds

No Comments

No Known Activations