INDEX

Explanations

references to locations and associated activities

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

anship

-0.17

 sÃ¡t

-0.16

 lodging

-0.16

dÄ±

-0.15

 Erick

-0.14

ptime

-0.14

/vendors

-0.14

ãĤ·ãĥ¼

-0.14

KV

-0.14

ifth

-0.14

POSITIVE LOGITS

Tes

0.34

 Marks

0.30

Tes

0.28

tes

0.27

 Boots

0.27

ASD

0.24

 Virgin

0.24

Marks

0.23

 Wait

0.23

MSE

0.23

Activations Density 0.298%

references to locations and associated activities

No Comments

No Known Activations