INDEX

Explanations

references to different forms or types of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 Formation

-0.16

 formation

-0.16

ety

-0.15

Pager

-0.15

Formation

-0.15

/moment

-0.14

ffects

-0.14

IAL

-0.14

ãģ

-0.14

ILER

-0.14

POSITIVE LOGITS

idable

0.26

ulary

0.24

ulating

0.23

ulas

0.23

íĥľ

0.23

atters

0.22

ative

0.22

aggio

0.20

ulates

0.20

-urlencoded

0.19

Activations Density 0.020%

references to different forms or types of something

No Comments

No Known Activations