INDEX

Explanations

references to concepts of wholeness or totality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

uled

-0.16

jen

-0.16

light

-0.16

UBL

-0.15

 subtype

-0.15

iest

-0.14

 certain

-0.14

ron

-0.14

iji

-0.14

illin

-0.14

POSITIVE LOGITS

 thing

0.28

ties

0.26

 spectrum

0.23

gam

0.22

pectrum

0.20

thing

0.20

heart

0.19

 Thing

0.19

Thing

0.19

 breadth

0.18

Activations Density 0.040%

references to concepts of wholeness or totality

No Comments

No Known Activations