INDEX

Explanations

elements related to properties and parameters in a markup or configuration context

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

anson

-0.16

 Mits

-0.15

edom

-0.14

Slash

-0.14

Cir

-0.14

ERSIST

-0.14

-0.13

 Dion

-0.13

Anc

-0.13

Anc

-0.13

POSITIVE LOGITS

TURE

0.16

íĴį

0.15

 Coron

0.14

Pref

0.14

å½¼

0.14

:host

0.13

jn

0.13

stery

0.13

:Number

0.13

uhe

0.13

Activations Density 0.016%

elements related to properties and parameters in a markup or configuration context

No Comments

No Known Activations