INDEX

Explanations

phrases related to evidence-based approaches or practices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ross

-0.15

cht

-0.14

atch

-0.14

ogan

-0.14

vron

-0.14

à¸Ķà¸¢

-0.13

 Analog

-0.13

Vin

-0.13

acht

-0.13

vince

-0.13

POSITIVE LOGITS

.ali

0.16

.od

0.15

Stretch

0.15

erli

0.14

idget

0.14

.plist

0.14

ony

0.14

bere

0.14

ract

0.14

Activations Density 0.005%

phrases related to evidence-based approaches or practices

No Comments

No Known Activations