INDEX

Explanations

names of people associated with notable events or actions

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

alet

-0.22

-0.21

-0.20

gaard

-0.20

gate

-0.19

yd

-0.19

gi

-0.19

Ð¸

-0.17

ÛĮ

-0.17

tal

-0.17

POSITIVE LOGITS

cre

0.20

eful

0.19

eph

0.18

imals

0.17

tr

0.17

alysis

0.17

à¸£à¸ĩ

0.16

iqu

0.16

eco

0.16

Ã¤s

0.16

Activations Density 0.018%

names of people associated with notable events or actions

No Comments

No Known Activations