INDEX

Explanations

references to professional teams and their qualifications or roles

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

ucch

-0.17

haven

-0.14

haps

-0.14

ÑīÐ¸

-0.14

.Networking

-0.14

ÅĻiv

-0.13

 necessity

-0.13

iamond

-0.13

 é¾

-0.13

woff

-0.13

POSITIVE LOGITS

 understand

0.27

 possess

0.25

 understands

0.23

 tail

0.23

 pride

0.22

poss

0.21

 poss

0.20

 offer

0.20

 Understand

0.20

pr

0.20

Activations Density 0.091%

references to professional teams and their qualifications or roles

No Comments

No Known Activations