INDEX

Explanations

instances of the word "hum" and its variations, indicating a focus on humility or humility-related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

yonel

-0.19

hell

-0.17

ncia

-0.17

upo

-0.17

anje

-0.16

ÐµÐ½ÑĮ

-0.15

adem

-0.15

legate

-0.15

oler

-0.15

ÏĩÎ®

-0.15

POSITIVE LOGITS

pty

0.31

ankind

0.28

bug

0.27

iliated

0.27

iliate

0.26

mock

0.25

mus

0.25

mers

0.24

mer

0.23

bling

0.23

Activations Density 0.008%

instances of the word "hum" and its variations, indicating a focus on humility or humility-related concepts

No Comments

No Known Activations