INDEX

Explanations

references to funding and support for projects or initiatives

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

ĺìĿ´

-0.16

enant

-0.15

.azure

-0.15

hart

-0.15

anych

-0.14

.signIn

-0.13

ãĤ«ãĥ¼

-0.13

 Ð°Ð±ÑģÐ¾Ð»ÑİÑĤ

-0.13

levation

-0.13

isphere

-0.13

POSITIVE LOGITS

 Pony

0.15

 cease

0.15

oria

0.15

zew

0.15

 pony

0.15

orian

0.14

å·

0.14

den

0.14

quip

0.14

lod

0.14

Activations Density 0.009%

references to funding and support for projects or initiatives

No Comments

No Known Activations