INDEX

Explanations

references to medical research and publications

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

ubre

-0.16

rup

-0.16

 Rupert

-0.15

IQ

-0.14

 constit

-0.14

er

-0.14

rade

-0.14

 spare

-0.14

Ev

-0.14

 Ware

-0.14

POSITIVE LOGITS

abox

0.17

ApplicationBuilder

0.17

0.15

ABCDEFGHIJKLMNOP

0.15

areth

0.15

.googlecode

0.15

_exact

0.14

ootball

0.14

æ²³

0.14

-US

0.14

Activations Density 0.001%

references to medical research and publications

No Comments

No Known Activations