INDEX

Explanations

words and phrases indicating urgency or significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

irim

-0.16

ells

-0.15

ernes

-0.15

 Ludwig

-0.15

ersen

-0.15

undo

-0.15

 Walton

-0.15

 crust

-0.15

yps

-0.15

-0.14

POSITIVE LOGITS

ingles

0.18

 wash

0.16

Ã¡ch

0.15

ÐµÑģÐ¸

0.15

inski

0.15

 sink

0.15

avr

0.15

Sink

0.15

 Sink

0.14

iad

0.14

Activations Density 0.031%

words and phrases indicating urgency or significance

No Comments

No Known Activations