INDEX

Explanations

inquiries and information about travel options and accommodations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

rawer

-0.16

ÑĩÑĥÐº

-0.16

ces

-0.16

elmet

-0.15

utar

-0.15

ToWorld

-0.14

edido

-0.14

xis

-0.14

hee

-0.14

POSITIVE LOGITS

 difference

0.15

 Grass

0.14

 shoulders

0.14

 Vine

0.14

.removeAll

0.14

 Baths

0.14

irt

0.14

inas

0.13

baum

0.13

 Richards

0.13

Activations Density 0.012%

inquiries and information about travel options and accommodations

No Comments

No Known Activations