INDEX

Explanations

references to foundations, organizations, or established entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

rok

-0.16

ohl

-0.16

.wp

-0.15

usaha

-0.14

 dimensions

-0.14

ander

-0.14

echa

-0.14

KHR

-0.14

upert

-0.14

esin

-0.14

POSITIVE LOGITS

issy

0.18

azor

0.15

setParameter

0.15

istes

0.14

ines

0.14

ipse

0.14

Äĥm

0.14

initializer

0.14

 Elliot

0.13

trimmed

0.13

Activations Density 0.026%

references to foundations, organizations, or established entities

No Comments

No Known Activations