INDEX

Explanations

details related to accommodations and lodging features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

Bip

-0.15

icy

-0.15

Die

-0.14

jni

-0.14

-0.13

 Ù¾Úĺ

-0.13

CHAN

-0.13

 wart

-0.13

 Butt

-0.13

agent

-0.13

POSITIVE LOGITS

fut

0.24

 fold

0.24

 twin

0.24

 Murphy

0.24

 Twin

0.22

 pull

0.22

mur

0.22

 twins

0.21

 Pull

0.21

Fut

0.20

Activations Density 0.021%

details related to accommodations and lodging features

No Comments

No Known Activations