INDEX

Explanations

terms related to measurements and changes in amplitude or intensity in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ANEL

-0.20

bies

-0.17

apult

-0.16

anel

-0.15

ecies

-0.15

lu

-0.15

åĥı

-0.15

../../../

-0.14

PLE

-0.14

æ®

-0.14

POSITIVE LOGITS

plitude

0.21

ishly

0.19

ish

0.19

 Ende

0.18

stery

0.18

ethyst

0.17

sterdam

0.17

é®®

0.17

é²ľ

0.17

plit

0.17

Activations Density 0.064%

terms related to measurements and changes in amplitude or intensity in various contexts

No Comments

No Known Activations