INDEX

Explanations

specific names, entities, or proper nouns related to individuals or organizations

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

add

-0.20

ate

-0.18

ee

-0.18

all

-0.18

ase

-0.18

ail

-0.18

ant

-0.17

ass

-0.17

et

-0.17

ado

-0.17

POSITIVE LOGITS

zburg

0.25

sburg

0.24

burg

0.23

lymp

0.22

burgh

0.22

ksen

0.21

recht

0.21

strup

0.21

zheimer

0.21

chwitz

0.21

Activations Density 0.032%

specific names, entities, or proper nouns related to individuals or organizations

No Comments

No Known Activations