INDEX

Explanations

instances of specific keywords and phrases related to names, locations, and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 Hammond

-0.17

UNG

-0.16

-0.15

ialis

-0.15

 Cornel

-0.14

ows

-0.14

YLON

-0.14

åĲ

-0.14

ung

-0.14

POSITIVE LOGITS

hiba

0.18

inded

0.17

adera

0.17

 Huang

0.16

'gc

0.16

à¸Ńà¸Ļ

0.15

 Turnbull

0.15

Esk

0.14

usty

0.14

ëĤł

0.14

Activations Density 0.008%

instances of specific keywords and phrases related to names, locations, and entities

No Comments

No Known Activations