INDEX

Explanations

terms related to parameters and their various contexts in technical settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

lake

-0.15

ê°Ĳ

-0.14

Ã©p

-0.14

Ä©a

-0.14

mented

-0.14

arrants

-0.14

riages

-0.14

Ãłi

-0.14

zag

-0.14

poons

-0.13

POSITIVE LOGITS

ilitary

0.28

etric

0.27

agnetic

0.23

ters

0.23

ater

0.22

edics

0.21

para

0.20

ount

0.20

aters

0.20

etr

0.20

Activations Density 0.012%

terms related to parameters and their various contexts in technical settings

No Comments

No Known Activations