INDEX

Explanations

terms and phrases related to boredom or monotony

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

ces

-0.18

endoza

-0.17

ven

-0.16

WX

-0.14

 Integration

-0.14

bilt

-0.14

burn

-0.14

abal

-0.14

ÏĥÏĢ

-0.14

POSITIVE LOGITS

sville

0.16

agan

0.15

ARRIER

0.15

 Ride

0.15

wig

0.15

din

0.15

sed

0.14

inflate

0.13

hus

0.13

iang

0.13

Activations Density 0.066%

terms and phrases related to boredom or monotony

No Comments

No Known Activations