INDEX

Explanations

references to significant dates and times

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

arge

-0.16

obb

-0.16

 Calder

-0.14

gger

-0.14

elen

-0.14

enza

-0.14

 Palmer

-0.14

Prostit

-0.14

omers

-0.14

adora

-0.14

POSITIVE LOGITS

ainless

0.17

uro

0.17

%#

0.16

uros

0.15

isha

0.14

 Rehab

0.13

undy

0.13

 HÃ²a

0.13

tro

0.13

.SetValue

0.13

Activations Density 0.022%

references to significant dates and times

No Comments

No Known Activations