INDEX

Explanations

concepts related to health and well-being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

Æ°u

-0.15

ÃĹ</

-0.14

 ÙĤØ·

-0.14

ijken

-0.14

cie

-0.14

atus

-0.14

 slova

-0.14

æ¿ĥ

-0.14

aldo

-0.14

atel

-0.13

POSITIVE LOGITS

.scalablytyped

0.18

 Barnett

0.15

aser

0.14

Tom

0.14

 Conserv

0.14

icom

0.14

 gang

0.13

aro

0.13

olv

0.13

Mar

0.13

Activations Density 0.038%

concepts related to health and well-being

No Comments

No Known Activations